Hugging Face's logo

timaeus
/
jaxgmg2_3phase_optim_state_patt

Model card Files
xet
 Community
davidquarel commited on
Commit
fb44126
·
verified ·
1 Parent(s): b2e2b64

Upload folder using huggingface_hub

Browse files
Files changed (13) hide show
  1. al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0/action_logprobs.pth.gz +3 -0
  2. al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0/action_probs.tar.gz +3 -0
  3. al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0/checkpoints.tar.gz +3 -0
  4. al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0/config.cfg +78 -0
  5. al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0/config.json +80 -0
  6. al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0/eval.jsonl +0 -0
  7. al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0/eval.log +178 -0
  8. al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0/latest_train.json +12 -0
  9. al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0/patterning.log +52 -0
  10. al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0/setup.json +95 -0
  11. al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0/setup.txt +8 -0
  12. al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0/train.jsonl +178 -0
  13. al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0/train.log +178 -0
al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0/action_logprobs.pth.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4a000e30c38a7acfadcaaf119bd3f21b6d2be523c06ae8b143845aa99d48b6d
3
+ size 10525546
al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0/action_probs.tar.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c543b81331c54cde7a252b0768aef3a1135a8423385f0369b30d76eb074f0cb
3
+ size 9088703
al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0/checkpoints.tar.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c7c305e627b1a2197b9b23d2b2d1838ad429f8ec5cec575e47eaa0924b95284
3
+ size 59272167
al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0/config.cfg ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ rl_action=train
2
+ model_type=impala
3
+ lr=5e-05
4
+ discount_rate=0.99
5
+ num_rollout_steps=64
6
+ grad_acc_per_chunk=4
7
+ num_rollout_chunks=1
8
+ cheese_loc=any
9
+ env_layout=open
10
+ alpha=0.1966666666666666
11
+ env_size=13
12
+ num_levels=9600
13
+ compile=True
14
+ use_prev_action=False
15
+ weight_restrictions=None
16
+ weight_restrictions_invert=False
17
+ use_bf16=False
18
+ use_wandb=True
19
+ seed=42
20
+ mask_type=first_episode
21
+ ckpt_dir=jaxgmg2_3phase_optim_state_patt
22
+ vis_average_state=False
23
+ trim_episodes=False
24
+ num_total_env_steps=50000000
25
+ eval_every=1
26
+ eff_horizon=None
27
+ optim=adam
28
+ env_rule=None
29
+ use_hf=True
30
+ use_log=True
31
+ log_optimizer_state=False
32
+ resume=jaxgmg2_3phase_optim_state/al_0.6_g_0.98_id_17_seed_980617
33
+ resume_id=3810
34
+ resume_optim=False
35
+ checkpoint=al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0
36
+ wandb_project=jaxgmg_test
37
+ eval_schedule=0:1
38
+ render_sixel=False
39
+ sixel_idx=60
40
+ live_monitor=False
41
+ run_id=0
42
+ seed_formula=None
43
+ deterministic=True
44
+ penalize_time=False
45
+ f_str_ckpt=None
46
+ duplication_factor=-1
47
+ smoke=False
48
+ ntfy=None
49
+ num_chains=6
50
+ num_draws=3000
51
+ num_steps_bw_draws=1
52
+ on_policy=True
53
+ llc_nbeta=3000
54
+ localization=10
55
+ exact_solver_each_draw=False
56
+ llc_optimizer=sgld
57
+ iw_clip_eps=None
58
+ rmsprop_burnin_steps=20
59
+ llc_data_file=llc_scan_open_reinforce.pkl
60
+ llc_checkpoint_index=None
61
+ llc_checkpoint_number=None
62
+ sink=None
63
+ repo_id=davidquarel/jaxgmg_ckpt_zip
64
+ use_shuffled_checkpoints=False
65
+ force_re_download=False
66
+ off_distribution_data=False
67
+ evaluate_every_position=False
68
+ num_prev_actions=1
69
+ eff_acc_steps=4
70
+ chunk_size=9600
71
+ env_steps_per_microbatch=153600
72
+ ckpt_path=jaxgmg2_3phase_optim_state_patt/al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0
73
+ env_steps_per_loop=614400
74
+ total_loops=81
75
+ patt_mode=diff
76
+ patt_h=-0.8
77
+ model_id=al_0.6_g_0.98_id_17_seed_980617
78
+ _patt_weights=None
al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0/config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_patt_weights": null,
3
+ "alpha": 0.1966666666666666,
4
+ "checkpoint": "al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0",
5
+ "cheese_loc": "any",
6
+ "chunk_size": 9600,
7
+ "ckpt_dir": "jaxgmg2_3phase_optim_state_patt",
8
+ "ckpt_path": "jaxgmg2_3phase_optim_state_patt/al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0",
9
+ "compile": true,
10
+ "deterministic": true,
11
+ "discount_rate": 0.99,
12
+ "duplication_factor": -1,
13
+ "eff_acc_steps": 4,
14
+ "eff_horizon": null,
15
+ "env_layout": "open",
16
+ "env_rule": null,
17
+ "env_size": 13,
18
+ "env_steps_per_loop": 614400,
19
+ "env_steps_per_microbatch": 153600,
20
+ "eval_every": 1,
21
+ "eval_schedule": "0:1",
22
+ "evaluate_every_position": false,
23
+ "exact_solver_each_draw": false,
24
+ "f_str_ckpt": null,
25
+ "force_re_download": false,
26
+ "grad_acc_per_chunk": 4,
27
+ "iw_clip_eps": null,
28
+ "live_monitor": false,
29
+ "llc_checkpoint_index": null,
30
+ "llc_checkpoint_number": null,
31
+ "llc_data_file": "llc_scan_open_reinforce.pkl",
32
+ "llc_nbeta": 3000,
33
+ "llc_optimizer": "sgld",
34
+ "localization": 10,
35
+ "log_optimizer_state": false,
36
+ "lr": 5e-05,
37
+ "mask_type": "first_episode",
38
+ "model_id": "al_0.6_g_0.98_id_17_seed_980617",
39
+ "model_type": "impala",
40
+ "ntfy": null,
41
+ "num_chains": 6,
42
+ "num_draws": 3000,
43
+ "num_levels": 9600,
44
+ "num_prev_actions": 1,
45
+ "num_rollout_chunks": 1,
46
+ "num_rollout_steps": 64,
47
+ "num_steps_bw_draws": 1,
48
+ "num_total_env_steps": 50000000,
49
+ "off_distribution_data": false,
50
+ "on_policy": true,
51
+ "optim": "adam",
52
+ "patt_h": -0.8,
53
+ "patt_mode": "diff",
54
+ "penalize_time": false,
55
+ "render_sixel": false,
56
+ "repo_id": "davidquarel/jaxgmg_ckpt_zip",
57
+ "resume": "jaxgmg2_3phase_optim_state/al_0.6_g_0.98_id_17_seed_980617",
58
+ "resume_id": 3810,
59
+ "resume_optim": false,
60
+ "rl_action": "train",
61
+ "rmsprop_burnin_steps": 20,
62
+ "run_id": 0,
63
+ "seed": 42,
64
+ "seed_formula": null,
65
+ "sink": null,
66
+ "sixel_idx": 60,
67
+ "smoke": false,
68
+ "total_loops": 81,
69
+ "trim_episodes": false,
70
+ "use_bf16": false,
71
+ "use_hf": true,
72
+ "use_log": true,
73
+ "use_prev_action": false,
74
+ "use_shuffled_checkpoints": false,
75
+ "use_wandb": true,
76
+ "vis_average_state": false,
77
+ "wandb_project": "jaxgmg_test",
78
+ "weight_restrictions": null,
79
+ "weight_restrictions_invert": false
80
+ }
al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0/eval.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0/eval.log ADDED
@@ -0,0 +1,178 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [2026-02-20T15:08:14.845604Z] Loop 0: Reg: 0.0043, AltReg: 0.0129, CorReg: 0.0022, TopReg: 0.0136, AllReg: 0.0129, BotRReg: 0.0152, OV: 0.9143, AltV: 0.9260, CorV: 0.9114, TopV: 0.9127, BotRV: 0.9110, AllV: 0.9260
2
+ [2026-02-20T15:08:15.877136Z] Loop 1: Reg: 0.0051, AltReg: 0.0172, CorReg: 0.0022, TopReg: 0.0172, AllReg: 0.0172, BotRReg: 0.0233, OV: 0.9135, AltV: 0.9217, CorV: 0.9115, TopV: 0.9090, BotRV: 0.9029, AllV: 0.9217
3
+ [2026-02-20T15:08:16.804431Z] Loop 2: Reg: 0.0050, AltReg: 0.0161, CorReg: 0.0023, TopReg: 0.0161, AllReg: 0.0161, BotRReg: 0.0207, OV: 0.9136, AltV: 0.9229, CorV: 0.9114, TopV: 0.9101, BotRV: 0.9055, AllV: 0.9229
4
+ [2026-02-20T15:08:17.728687Z] Loop 3: Reg: 0.0056, AltReg: 0.0170, CorReg: 0.0028, TopReg: 0.0168, AllReg: 0.0170, BotRReg: 0.0188, OV: 0.9130, AltV: 0.9220, CorV: 0.9108, TopV: 0.9094, BotRV: 0.9074, AllV: 0.9220
5
+ [2026-02-20T15:08:18.652886Z] Loop 4: Reg: 0.0074, AltReg: 0.0204, CorReg: 0.0042, TopReg: 0.0202, AllReg: 0.0204, BotRReg: 0.0180, OV: 0.9112, AltV: 0.9186, CorV: 0.9094, TopV: 0.9060, BotRV: 0.9082, AllV: 0.9186
6
+ [2026-02-20T15:08:19.577468Z] Loop 5: Reg: 0.0097, AltReg: 0.0245, CorReg: 0.0061, TopReg: 0.0245, AllReg: 0.0245, BotRReg: 0.0186, OV: 0.9089, AltV: 0.9144, CorV: 0.9075, TopV: 0.9018, BotRV: 0.9076, AllV: 0.9144
7
+ [2026-02-20T15:08:20.501024Z] Loop 6: Reg: 0.0081, AltReg: 0.0216, CorReg: 0.0048, TopReg: 0.0216, AllReg: 0.0216, BotRReg: 0.0178, OV: 0.9105, AltV: 0.9174, CorV: 0.9089, TopV: 0.9046, BotRV: 0.9084, AllV: 0.9174
8
+ [2026-02-20T15:08:21.424819Z] Loop 7: Reg: 0.0069, AltReg: 0.0195, CorReg: 0.0039, TopReg: 0.0191, AllReg: 0.0195, BotRReg: 0.0182, OV: 0.9117, AltV: 0.9195, CorV: 0.9098, TopV: 0.9071, BotRV: 0.9080, AllV: 0.9195
9
+ [2026-02-20T15:08:22.349274Z] Loop 8: Reg: 0.0059, AltReg: 0.0172, CorReg: 0.0031, TopReg: 0.0167, AllReg: 0.0172, BotRReg: 0.0175, OV: 0.9127, AltV: 0.9217, CorV: 0.9105, TopV: 0.9095, BotRV: 0.9087, AllV: 0.9217
10
+ [2026-02-20T15:08:23.275561Z] Loop 9: Reg: 0.0049, AltReg: 0.0149, CorReg: 0.0024, TopReg: 0.0143, AllReg: 0.0149, BotRReg: 0.0169, OV: 0.9137, AltV: 0.9240, CorV: 0.9112, TopV: 0.9119, BotRV: 0.9093, AllV: 0.9240
11
+ [2026-02-20T15:08:24.202290Z] Loop 10: Reg: 0.0044, AltReg: 0.0134, CorReg: 0.0022, TopReg: 0.0130, AllReg: 0.0134, BotRReg: 0.0162, OV: 0.9142, AltV: 0.9256, CorV: 0.9115, TopV: 0.9132, BotRV: 0.9100, AllV: 0.9256
12
+ [2026-02-20T15:08:25.124486Z] Loop 11: Reg: 0.0042, AltReg: 0.0129, CorReg: 0.0021, TopReg: 0.0126, AllReg: 0.0129, BotRReg: 0.0162, OV: 0.9144, AltV: 0.9261, CorV: 0.9115, TopV: 0.9136, BotRV: 0.9100, AllV: 0.9261
13
+ [2026-02-20T15:08:26.049182Z] Loop 12: Reg: 0.0042, AltReg: 0.0126, CorReg: 0.0021, TopReg: 0.0123, AllReg: 0.0126, BotRReg: 0.0167, OV: 0.9145, AltV: 0.9263, CorV: 0.9116, TopV: 0.9139, BotRV: 0.9095, AllV: 0.9263
14
+ [2026-02-20T15:08:26.970843Z] Loop 13: Reg: 0.0041, AltReg: 0.0127, CorReg: 0.0020, TopReg: 0.0122, AllReg: 0.0127, BotRReg: 0.0177, OV: 0.9145, AltV: 0.9263, CorV: 0.9116, TopV: 0.9140, BotRV: 0.9085, AllV: 0.9263
15
+ [2026-02-20T15:08:27.892848Z] Loop 14: Reg: 0.0042, AltReg: 0.0132, CorReg: 0.0020, TopReg: 0.0124, AllReg: 0.0132, BotRReg: 0.0197, OV: 0.9144, AltV: 0.9258, CorV: 0.9116, TopV: 0.9138, BotRV: 0.9065, AllV: 0.9258
16
+ [2026-02-20T15:08:28.816418Z] Loop 15: Reg: 0.0045, AltReg: 0.0152, CorReg: 0.0019, TopReg: 0.0133, AllReg: 0.0152, BotRReg: 0.0233, OV: 0.9141, AltV: 0.9238, CorV: 0.9117, TopV: 0.9129, BotRV: 0.9029, AllV: 0.9238
17
+ [2026-02-20T15:11:11.453375Z] Loop 0: Reg: 0.0043, AltReg: 0.0129, CorReg: 0.0022, TopReg: 0.0136, AllReg: 0.0129, BotRReg: 0.0152, OV: 0.9143, AltV: 0.9260, CorV: 0.9114, TopV: 0.9127, BotRV: 0.9110, AllV: 0.9260
18
+ [2026-02-20T15:11:12.492797Z] Loop 1: Reg: 0.0051, AltReg: 0.0172, CorReg: 0.0022, TopReg: 0.0172, AllReg: 0.0172, BotRReg: 0.0233, OV: 0.9135, AltV: 0.9217, CorV: 0.9115, TopV: 0.9090, BotRV: 0.9029, AllV: 0.9217
19
+ [2026-02-20T15:11:13.421779Z] Loop 2: Reg: 0.0050, AltReg: 0.0161, CorReg: 0.0023, TopReg: 0.0161, AllReg: 0.0161, BotRReg: 0.0207, OV: 0.9136, AltV: 0.9229, CorV: 0.9114, TopV: 0.9101, BotRV: 0.9055, AllV: 0.9229
20
+ [2026-02-20T15:11:14.349508Z] Loop 3: Reg: 0.0056, AltReg: 0.0170, CorReg: 0.0028, TopReg: 0.0168, AllReg: 0.0170, BotRReg: 0.0188, OV: 0.9130, AltV: 0.9220, CorV: 0.9108, TopV: 0.9094, BotRV: 0.9074, AllV: 0.9220
21
+ [2026-02-20T15:11:15.278046Z] Loop 4: Reg: 0.0074, AltReg: 0.0204, CorReg: 0.0042, TopReg: 0.0202, AllReg: 0.0204, BotRReg: 0.0180, OV: 0.9112, AltV: 0.9186, CorV: 0.9094, TopV: 0.9060, BotRV: 0.9082, AllV: 0.9186
22
+ [2026-02-20T15:11:16.212376Z] Loop 5: Reg: 0.0097, AltReg: 0.0245, CorReg: 0.0061, TopReg: 0.0245, AllReg: 0.0245, BotRReg: 0.0186, OV: 0.9089, AltV: 0.9144, CorV: 0.9075, TopV: 0.9018, BotRV: 0.9076, AllV: 0.9144
23
+ [2026-02-20T15:11:17.142682Z] Loop 6: Reg: 0.0081, AltReg: 0.0216, CorReg: 0.0048, TopReg: 0.0216, AllReg: 0.0216, BotRReg: 0.0178, OV: 0.9105, AltV: 0.9174, CorV: 0.9089, TopV: 0.9046, BotRV: 0.9084, AllV: 0.9174
24
+ [2026-02-20T15:11:18.073063Z] Loop 7: Reg: 0.0069, AltReg: 0.0195, CorReg: 0.0039, TopReg: 0.0191, AllReg: 0.0195, BotRReg: 0.0182, OV: 0.9117, AltV: 0.9195, CorV: 0.9098, TopV: 0.9071, BotRV: 0.9080, AllV: 0.9195
25
+ [2026-02-20T15:11:18.999376Z] Loop 8: Reg: 0.0059, AltReg: 0.0172, CorReg: 0.0031, TopReg: 0.0167, AllReg: 0.0172, BotRReg: 0.0175, OV: 0.9127, AltV: 0.9217, CorV: 0.9105, TopV: 0.9095, BotRV: 0.9087, AllV: 0.9217
26
+ [2026-02-20T15:11:19.925011Z] Loop 9: Reg: 0.0049, AltReg: 0.0149, CorReg: 0.0024, TopReg: 0.0143, AllReg: 0.0149, BotRReg: 0.0169, OV: 0.9137, AltV: 0.9240, CorV: 0.9112, TopV: 0.9119, BotRV: 0.9093, AllV: 0.9240
27
+ [2026-02-20T15:11:20.861112Z] Loop 10: Reg: 0.0044, AltReg: 0.0134, CorReg: 0.0022, TopReg: 0.0130, AllReg: 0.0134, BotRReg: 0.0162, OV: 0.9142, AltV: 0.9256, CorV: 0.9115, TopV: 0.9132, BotRV: 0.9100, AllV: 0.9256
28
+ [2026-02-20T15:11:21.784040Z] Loop 11: Reg: 0.0042, AltReg: 0.0129, CorReg: 0.0021, TopReg: 0.0126, AllReg: 0.0129, BotRReg: 0.0162, OV: 0.9144, AltV: 0.9261, CorV: 0.9115, TopV: 0.9136, BotRV: 0.9100, AllV: 0.9261
29
+ [2026-02-20T15:11:22.708756Z] Loop 12: Reg: 0.0042, AltReg: 0.0126, CorReg: 0.0021, TopReg: 0.0123, AllReg: 0.0126, BotRReg: 0.0167, OV: 0.9145, AltV: 0.9263, CorV: 0.9116, TopV: 0.9139, BotRV: 0.9095, AllV: 0.9263
30
+ [2026-02-20T15:11:23.633569Z] Loop 13: Reg: 0.0041, AltReg: 0.0127, CorReg: 0.0020, TopReg: 0.0122, AllReg: 0.0127, BotRReg: 0.0177, OV: 0.9145, AltV: 0.9263, CorV: 0.9116, TopV: 0.9140, BotRV: 0.9085, AllV: 0.9263
31
+ [2026-02-20T15:11:24.559172Z] Loop 14: Reg: 0.0042, AltReg: 0.0132, CorReg: 0.0020, TopReg: 0.0124, AllReg: 0.0132, BotRReg: 0.0197, OV: 0.9144, AltV: 0.9258, CorV: 0.9116, TopV: 0.9138, BotRV: 0.9065, AllV: 0.9258
32
+ [2026-02-20T15:11:25.484367Z] Loop 15: Reg: 0.0045, AltReg: 0.0152, CorReg: 0.0019, TopReg: 0.0133, AllReg: 0.0152, BotRReg: 0.0233, OV: 0.9141, AltV: 0.9238, CorV: 0.9117, TopV: 0.9129, BotRV: 0.9029, AllV: 0.9238
33
+ [2026-02-20T15:11:26.488116Z] Loop 16: Reg: 0.0052, AltReg: 0.0184, CorReg: 0.0019, TopReg: 0.0148, AllReg: 0.0184, BotRReg: 0.0281, OV: 0.9135, AltV: 0.9205, CorV: 0.9117, TopV: 0.9114, BotRV: 0.8981, AllV: 0.9205
34
+ [2026-02-20T15:11:27.422915Z] Loop 17: Reg: 0.0053, AltReg: 0.0189, CorReg: 0.0019, TopReg: 0.0148, AllReg: 0.0189, BotRReg: 0.0290, OV: 0.9134, AltV: 0.9201, CorV: 0.9117, TopV: 0.9114, BotRV: 0.8972, AllV: 0.9201
35
+ [2026-02-20T15:11:28.362104Z] Loop 18: Reg: 0.0051, AltReg: 0.0180, CorReg: 0.0019, TopReg: 0.0143, AllReg: 0.0180, BotRReg: 0.0283, OV: 0.9135, AltV: 0.9209, CorV: 0.9117, TopV: 0.9120, BotRV: 0.8979, AllV: 0.9209
36
+ [2026-02-20T15:11:29.292669Z] Loop 19: Reg: 0.0049, AltReg: 0.0170, CorReg: 0.0020, TopReg: 0.0136, AllReg: 0.0170, BotRReg: 0.0272, OV: 0.9137, AltV: 0.9220, CorV: 0.9117, TopV: 0.9126, BotRV: 0.8990, AllV: 0.9220
37
+ [2026-02-20T15:11:30.234154Z] Loop 20: Reg: 0.0049, AltReg: 0.0170, CorReg: 0.0020, TopReg: 0.0133, AllReg: 0.0170, BotRReg: 0.0277, OV: 0.9137, AltV: 0.9220, CorV: 0.9116, TopV: 0.9129, BotRV: 0.8985, AllV: 0.9220
38
+ [2026-02-20T15:11:31.157327Z] Loop 21: Reg: 0.0049, AltReg: 0.0167, CorReg: 0.0020, TopReg: 0.0131, AllReg: 0.0167, BotRReg: 0.0275, OV: 0.9137, AltV: 0.9223, CorV: 0.9116, TopV: 0.9131, BotRV: 0.8987, AllV: 0.9223
39
+ [2026-02-20T15:11:32.080229Z] Loop 22: Reg: 0.0048, AltReg: 0.0162, CorReg: 0.0020, TopReg: 0.0130, AllReg: 0.0162, BotRReg: 0.0272, OV: 0.9138, AltV: 0.9228, CorV: 0.9116, TopV: 0.9132, BotRV: 0.8990, AllV: 0.9228
40
+ [2026-02-20T15:11:33.005163Z] Loop 23: Reg: 0.0047, AltReg: 0.0154, CorReg: 0.0021, TopReg: 0.0128, AllReg: 0.0154, BotRReg: 0.0265, OV: 0.9139, AltV: 0.9235, CorV: 0.9116, TopV: 0.9134, BotRV: 0.8997, AllV: 0.9235
41
+ [2026-02-20T15:11:33.933512Z] Loop 24: Reg: 0.0047, AltReg: 0.0151, CorReg: 0.0022, TopReg: 0.0128, AllReg: 0.0151, BotRReg: 0.0265, OV: 0.9139, AltV: 0.9239, CorV: 0.9115, TopV: 0.9134, BotRV: 0.8997, AllV: 0.9239
42
+ [2026-02-20T15:11:34.870315Z] Loop 25: Reg: 0.0049, AltReg: 0.0156, CorReg: 0.0023, TopReg: 0.0136, AllReg: 0.0156, BotRReg: 0.0276, OV: 0.9137, AltV: 0.9234, CorV: 0.9113, TopV: 0.9126, BotRV: 0.8986, AllV: 0.9234
43
+ [2026-02-20T15:11:35.795800Z] Loop 26: Reg: 0.0055, AltReg: 0.0180, CorReg: 0.0025, TopReg: 0.0163, AllReg: 0.0180, BotRReg: 0.0304, OV: 0.9131, AltV: 0.9210, CorV: 0.9111, TopV: 0.9099, BotRV: 0.8958, AllV: 0.9210
44
+ [2026-02-20T15:11:36.721489Z] Loop 27: Reg: 0.0060, AltReg: 0.0201, CorReg: 0.0025, TopReg: 0.0177, AllReg: 0.0201, BotRReg: 0.0339, OV: 0.9126, AltV: 0.9188, CorV: 0.9111, TopV: 0.9085, BotRV: 0.8923, AllV: 0.9188
45
+ [2026-02-20T15:11:37.646783Z] Loop 28: Reg: 0.0062, AltReg: 0.0206, CorReg: 0.0027, TopReg: 0.0187, AllReg: 0.0206, BotRReg: 0.0329, OV: 0.9124, AltV: 0.9183, CorV: 0.9110, TopV: 0.9075, BotRV: 0.8933, AllV: 0.9183
46
+ [2026-02-20T15:11:38.572416Z] Loop 29: Reg: 0.0065, AltReg: 0.0223, CorReg: 0.0026, TopReg: 0.0207, AllReg: 0.0223, BotRReg: 0.0344, OV: 0.9121, AltV: 0.9167, CorV: 0.9110, TopV: 0.9055, BotRV: 0.8918, AllV: 0.9167
47
+ [2026-02-20T15:11:39.498066Z] Loop 30: Reg: 0.0063, AltReg: 0.0216, CorReg: 0.0026, TopReg: 0.0206, AllReg: 0.0216, BotRReg: 0.0332, OV: 0.9123, AltV: 0.9174, CorV: 0.9111, TopV: 0.9056, BotRV: 0.8930, AllV: 0.9174
48
+ [2026-02-20T15:11:40.425378Z] Loop 31: Reg: 0.0063, AltReg: 0.0219, CorReg: 0.0025, TopReg: 0.0206, AllReg: 0.0219, BotRReg: 0.0349, OV: 0.9123, AltV: 0.9171, CorV: 0.9112, TopV: 0.9056, BotRV: 0.8913, AllV: 0.9171
49
+ [2026-02-20T15:11:41.351434Z] Loop 32: Reg: 0.0062, AltReg: 0.0218, CorReg: 0.0024, TopReg: 0.0203, AllReg: 0.0218, BotRReg: 0.0353, OV: 0.9124, AltV: 0.9172, CorV: 0.9113, TopV: 0.9060, BotRV: 0.8910, AllV: 0.9172
50
+ [2026-02-20T15:11:42.277493Z] Loop 33: Reg: 0.0057, AltReg: 0.0196, CorReg: 0.0023, TopReg: 0.0188, AllReg: 0.0196, BotRReg: 0.0314, OV: 0.9129, AltV: 0.9194, CorV: 0.9113, TopV: 0.9074, BotRV: 0.8948, AllV: 0.9194
51
+ [2026-02-20T15:11:43.203388Z] Loop 34: Reg: 0.0053, AltReg: 0.0177, CorReg: 0.0023, TopReg: 0.0175, AllReg: 0.0177, BotRReg: 0.0280, OV: 0.9133, AltV: 0.9213, CorV: 0.9114, TopV: 0.9087, BotRV: 0.8982, AllV: 0.9213
52
+ [2026-02-20T15:11:44.129558Z] Loop 35: Reg: 0.0049, AltReg: 0.0155, CorReg: 0.0023, TopReg: 0.0159, AllReg: 0.0155, BotRReg: 0.0237, OV: 0.9137, AltV: 0.9234, CorV: 0.9113, TopV: 0.9103, BotRV: 0.9025, AllV: 0.9234
53
+ [2026-02-20T15:11:45.055995Z] Loop 36: Reg: 0.0047, AltReg: 0.0140, CorReg: 0.0024, TopReg: 0.0148, AllReg: 0.0140, BotRReg: 0.0205, OV: 0.9140, AltV: 0.9249, CorV: 0.9113, TopV: 0.9114, BotRV: 0.9058, AllV: 0.9249
54
+ [2026-02-20T15:11:45.983019Z] Loop 37: Reg: 0.0045, AltReg: 0.0130, CorReg: 0.0024, TopReg: 0.0141, AllReg: 0.0130, BotRReg: 0.0175, OV: 0.9141, AltV: 0.9259, CorV: 0.9112, TopV: 0.9121, BotRV: 0.9087, AllV: 0.9259
55
+ [2026-02-20T15:11:46.909167Z] Loop 38: Reg: 0.0044, AltReg: 0.0128, CorReg: 0.0024, TopReg: 0.0140, AllReg: 0.0128, BotRReg: 0.0163, OV: 0.9142, AltV: 0.9261, CorV: 0.9113, TopV: 0.9122, BotRV: 0.9099, AllV: 0.9261
56
+ [2026-02-20T15:11:47.834049Z] Loop 39: Reg: 0.0044, AltReg: 0.0128, CorReg: 0.0024, TopReg: 0.0139, AllReg: 0.0128, BotRReg: 0.0159, OV: 0.9142, AltV: 0.9262, CorV: 0.9113, TopV: 0.9123, BotRV: 0.9103, AllV: 0.9262
57
+ [2026-02-20T15:11:48.759920Z] Loop 40: Reg: 0.0044, AltReg: 0.0128, CorReg: 0.0023, TopReg: 0.0139, AllReg: 0.0128, BotRReg: 0.0158, OV: 0.9142, AltV: 0.9262, CorV: 0.9113, TopV: 0.9124, BotRV: 0.9104, AllV: 0.9262
58
+ [2026-02-20T15:11:49.687459Z] Loop 41: Reg: 0.0043, AltReg: 0.0127, CorReg: 0.0023, TopReg: 0.0137, AllReg: 0.0127, BotRReg: 0.0160, OV: 0.9143, AltV: 0.9263, CorV: 0.9114, TopV: 0.9126, BotRV: 0.9102, AllV: 0.9263
59
+ [2026-02-20T15:11:50.613376Z] Loop 42: Reg: 0.0042, AltReg: 0.0125, CorReg: 0.0022, TopReg: 0.0133, AllReg: 0.0125, BotRReg: 0.0165, OV: 0.9144, AltV: 0.9264, CorV: 0.9115, TopV: 0.9129, BotRV: 0.9097, AllV: 0.9264
60
+ [2026-02-20T15:11:51.540476Z] Loop 43: Reg: 0.0042, AltReg: 0.0126, CorReg: 0.0021, TopReg: 0.0130, AllReg: 0.0126, BotRReg: 0.0175, OV: 0.9145, AltV: 0.9264, CorV: 0.9115, TopV: 0.9132, BotRV: 0.9087, AllV: 0.9264
61
+ [2026-02-20T15:11:52.467572Z] Loop 44: Reg: 0.0041, AltReg: 0.0129, CorReg: 0.0020, TopReg: 0.0127, AllReg: 0.0129, BotRReg: 0.0190, OV: 0.9145, AltV: 0.9261, CorV: 0.9117, TopV: 0.9135, BotRV: 0.9073, AllV: 0.9261
62
+ [2026-02-20T15:11:53.394186Z] Loop 45: Reg: 0.0042, AltReg: 0.0138, CorReg: 0.0019, TopReg: 0.0128, AllReg: 0.0138, BotRReg: 0.0206, OV: 0.9144, AltV: 0.9251, CorV: 0.9117, TopV: 0.9134, BotRV: 0.9056, AllV: 0.9251
63
+ [2026-02-20T15:11:54.320604Z] Loop 46: Reg: 0.0045, AltReg: 0.0153, CorReg: 0.0018, TopReg: 0.0131, AllReg: 0.0153, BotRReg: 0.0226, OV: 0.9141, AltV: 0.9236, CorV: 0.9118, TopV: 0.9131, BotRV: 0.9036, AllV: 0.9236
64
+ [2026-02-20T15:11:55.253904Z] Loop 47: Reg: 0.0048, AltReg: 0.0170, CorReg: 0.0018, TopReg: 0.0138, AllReg: 0.0170, BotRReg: 0.0246, OV: 0.9138, AltV: 0.9220, CorV: 0.9119, TopV: 0.9124, BotRV: 0.9016, AllV: 0.9220
65
+ [2026-02-20T15:11:56.178895Z] Loop 48: Reg: 0.0051, AltReg: 0.0188, CorReg: 0.0018, TopReg: 0.0144, AllReg: 0.0188, BotRReg: 0.0262, OV: 0.9135, AltV: 0.9201, CorV: 0.9119, TopV: 0.9118, BotRV: 0.9000, AllV: 0.9201
66
+ [2026-02-20T15:11:57.101552Z] Loop 49: Reg: 0.0057, AltReg: 0.0220, CorReg: 0.0017, TopReg: 0.0153, AllReg: 0.0220, BotRReg: 0.0282, OV: 0.9129, AltV: 0.9169, CorV: 0.9119, TopV: 0.9109, BotRV: 0.8980, AllV: 0.9169
67
+ [2026-02-20T15:11:58.028577Z] Loop 50: Reg: 0.0056, AltReg: 0.0216, CorReg: 0.0017, TopReg: 0.0150, AllReg: 0.0216, BotRReg: 0.0274, OV: 0.9130, AltV: 0.9174, CorV: 0.9119, TopV: 0.9113, BotRV: 0.8988, AllV: 0.9174
68
+ [2026-02-20T15:11:58.954010Z] Loop 51: Reg: 0.0055, AltReg: 0.0206, CorReg: 0.0017, TopReg: 0.0147, AllReg: 0.0206, BotRReg: 0.0262, OV: 0.9132, AltV: 0.9183, CorV: 0.9119, TopV: 0.9115, BotRV: 0.9000, AllV: 0.9183
69
+ [2026-02-20T15:11:59.879684Z] Loop 52: Reg: 0.0051, AltReg: 0.0189, CorReg: 0.0018, TopReg: 0.0145, AllReg: 0.0189, BotRReg: 0.0244, OV: 0.9135, AltV: 0.9201, CorV: 0.9119, TopV: 0.9117, BotRV: 0.9018, AllV: 0.9201
70
+ [2026-02-20T15:12:00.806451Z] Loop 53: Reg: 0.0048, AltReg: 0.0168, CorReg: 0.0018, TopReg: 0.0149, AllReg: 0.0168, BotRReg: 0.0222, OV: 0.9139, AltV: 0.9222, CorV: 0.9118, TopV: 0.9114, BotRV: 0.9041, AllV: 0.9222
71
+ [2026-02-20T15:12:01.734381Z] Loop 54: Reg: 0.0046, AltReg: 0.0155, CorReg: 0.0019, TopReg: 0.0155, AllReg: 0.0155, BotRReg: 0.0205, OV: 0.9141, AltV: 0.9235, CorV: 0.9118, TopV: 0.9107, BotRV: 0.9057, AllV: 0.9235
72
+ [2026-02-20T15:12:02.661724Z] Loop 55: Reg: 0.0046, AltReg: 0.0153, CorReg: 0.0020, TopReg: 0.0171, AllReg: 0.0153, BotRReg: 0.0196, OV: 0.9140, AltV: 0.9237, CorV: 0.9117, TopV: 0.9091, BotRV: 0.9067, AllV: 0.9237
73
+ [2026-02-20T15:12:03.589081Z] Loop 56: Reg: 0.0048, AltReg: 0.0161, CorReg: 0.0021, TopReg: 0.0191, AllReg: 0.0161, BotRReg: 0.0198, OV: 0.9138, AltV: 0.9228, CorV: 0.9116, TopV: 0.9071, BotRV: 0.9065, AllV: 0.9228
74
+ [2026-02-20T15:12:04.517934Z] Loop 57: Reg: 0.0049, AltReg: 0.0163, CorReg: 0.0021, TopReg: 0.0193, AllReg: 0.0163, BotRReg: 0.0200, OV: 0.9137, AltV: 0.9226, CorV: 0.9115, TopV: 0.9069, BotRV: 0.9062, AllV: 0.9226
75
+ [2026-02-20T15:12:05.444289Z] Loop 58: Reg: 0.0049, AltReg: 0.0163, CorReg: 0.0021, TopReg: 0.0184, AllReg: 0.0163, BotRReg: 0.0204, OV: 0.9138, AltV: 0.9226, CorV: 0.9116, TopV: 0.9078, BotRV: 0.9058, AllV: 0.9226
76
+ [2026-02-20T15:12:06.374821Z] Loop 59: Reg: 0.0047, AltReg: 0.0154, CorReg: 0.0020, TopReg: 0.0166, AllReg: 0.0154, BotRReg: 0.0199, OV: 0.9140, AltV: 0.9236, CorV: 0.9116, TopV: 0.9096, BotRV: 0.9063, AllV: 0.9236
77
+ [2026-02-20T15:12:07.305144Z] Loop 60: Reg: 0.0045, AltReg: 0.0147, CorReg: 0.0020, TopReg: 0.0156, AllReg: 0.0147, BotRReg: 0.0195, OV: 0.9141, AltV: 0.9243, CorV: 0.9116, TopV: 0.9106, BotRV: 0.9067, AllV: 0.9243
78
+ [2026-02-20T15:12:08.237435Z] Loop 61: Reg: 0.0044, AltReg: 0.0140, CorReg: 0.0021, TopReg: 0.0150, AllReg: 0.0140, BotRReg: 0.0185, OV: 0.9142, AltV: 0.9250, CorV: 0.9115, TopV: 0.9112, BotRV: 0.9077, AllV: 0.9250
79
+ [2026-02-20T15:12:09.169228Z] Loop 62: Reg: 0.0044, AltReg: 0.0136, CorReg: 0.0021, TopReg: 0.0147, AllReg: 0.0136, BotRReg: 0.0180, OV: 0.9142, AltV: 0.9253, CorV: 0.9115, TopV: 0.9116, BotRV: 0.9083, AllV: 0.9253
80
+ [2026-02-20T15:12:10.099368Z] Loop 63: Reg: 0.0043, AltReg: 0.0132, CorReg: 0.0022, TopReg: 0.0142, AllReg: 0.0132, BotRReg: 0.0175, OV: 0.9143, AltV: 0.9257, CorV: 0.9115, TopV: 0.9121, BotRV: 0.9087, AllV: 0.9257
81
+ [2026-02-20T15:12:11.028936Z] Loop 64: Reg: 0.0043, AltReg: 0.0129, CorReg: 0.0021, TopReg: 0.0135, AllReg: 0.0129, BotRReg: 0.0174, OV: 0.9144, AltV: 0.9261, CorV: 0.9115, TopV: 0.9127, BotRV: 0.9088, AllV: 0.9261
82
+ [2026-02-20T15:12:11.958588Z] Loop 65: Reg: 0.0042, AltReg: 0.0127, CorReg: 0.0021, TopReg: 0.0130, AllReg: 0.0127, BotRReg: 0.0173, OV: 0.9144, AltV: 0.9263, CorV: 0.9115, TopV: 0.9132, BotRV: 0.9089, AllV: 0.9263
83
+ [2026-02-20T15:12:12.886480Z] Loop 66: Reg: 0.0042, AltReg: 0.0129, CorReg: 0.0021, TopReg: 0.0130, AllReg: 0.0129, BotRReg: 0.0180, OV: 0.9144, AltV: 0.9260, CorV: 0.9116, TopV: 0.9132, BotRV: 0.9082, AllV: 0.9260
84
+ [2026-02-20T15:12:13.820366Z] Loop 67: Reg: 0.0043, AltReg: 0.0138, CorReg: 0.0020, TopReg: 0.0134, AllReg: 0.0138, BotRReg: 0.0197, OV: 0.9143, AltV: 0.9252, CorV: 0.9116, TopV: 0.9128, BotRV: 0.9065, AllV: 0.9252
85
+ [2026-02-20T15:12:14.749593Z] Loop 68: Reg: 0.0045, AltReg: 0.0151, CorReg: 0.0020, TopReg: 0.0139, AllReg: 0.0151, BotRReg: 0.0216, OV: 0.9141, AltV: 0.9239, CorV: 0.9117, TopV: 0.9123, BotRV: 0.9046, AllV: 0.9239
86
+ [2026-02-20T15:12:15.678262Z] Loop 69: Reg: 0.0048, AltReg: 0.0163, CorReg: 0.0019, TopReg: 0.0143, AllReg: 0.0163, BotRReg: 0.0233, OV: 0.9139, AltV: 0.9227, CorV: 0.9117, TopV: 0.9119, BotRV: 0.9029, AllV: 0.9227
87
+ [2026-02-20T15:12:16.607679Z] Loop 70: Reg: 0.0047, AltReg: 0.0161, CorReg: 0.0019, TopReg: 0.0140, AllReg: 0.0161, BotRReg: 0.0234, OV: 0.9139, AltV: 0.9228, CorV: 0.9117, TopV: 0.9122, BotRV: 0.9028, AllV: 0.9228
88
+ [2026-02-20T15:12:17.535653Z] Loop 71: Reg: 0.0046, AltReg: 0.0155, CorReg: 0.0019, TopReg: 0.0134, AllReg: 0.0155, BotRReg: 0.0229, OV: 0.9140, AltV: 0.9234, CorV: 0.9117, TopV: 0.9128, BotRV: 0.9033, AllV: 0.9234
89
+ [2026-02-20T15:12:18.463263Z] Loop 72: Reg: 0.0046, AltReg: 0.0155, CorReg: 0.0019, TopReg: 0.0130, AllReg: 0.0155, BotRReg: 0.0231, OV: 0.9141, AltV: 0.9235, CorV: 0.9118, TopV: 0.9132, BotRV: 0.9031, AllV: 0.9235
90
+ [2026-02-20T15:12:19.392887Z] Loop 73: Reg: 0.0045, AltReg: 0.0150, CorReg: 0.0019, TopReg: 0.0129, AllReg: 0.0150, BotRReg: 0.0227, OV: 0.9142, AltV: 0.9239, CorV: 0.9118, TopV: 0.9133, BotRV: 0.9036, AllV: 0.9239
91
+ [2026-02-20T15:12:20.319800Z] Loop 74: Reg: 0.0043, AltReg: 0.0142, CorReg: 0.0019, TopReg: 0.0129, AllReg: 0.0142, BotRReg: 0.0214, OV: 0.9143, AltV: 0.9247, CorV: 0.9118, TopV: 0.9133, BotRV: 0.9048, AllV: 0.9247
92
+ [2026-02-20T15:12:21.246575Z] Loop 75: Reg: 0.0041, AltReg: 0.0130, CorReg: 0.0019, TopReg: 0.0128, AllReg: 0.0130, BotRReg: 0.0194, OV: 0.9145, AltV: 0.9259, CorV: 0.9117, TopV: 0.9134, BotRV: 0.9068, AllV: 0.9259
93
+ [2026-02-20T15:12:22.174696Z] Loop 76: Reg: 0.0040, AltReg: 0.0123, CorReg: 0.0020, TopReg: 0.0127, AllReg: 0.0123, BotRReg: 0.0182, OV: 0.9146, AltV: 0.9266, CorV: 0.9117, TopV: 0.9135, BotRV: 0.9081, AllV: 0.9266
94
+ [2026-02-20T15:12:23.102882Z] Loop 77: Reg: 0.0039, AltReg: 0.0119, CorReg: 0.0020, TopReg: 0.0127, AllReg: 0.0119, BotRReg: 0.0173, OV: 0.9147, AltV: 0.9270, CorV: 0.9117, TopV: 0.9135, BotRV: 0.9089, AllV: 0.9270
95
+ [2026-02-20T15:12:24.029079Z] Loop 78: Reg: 0.0039, AltReg: 0.0117, CorReg: 0.0020, TopReg: 0.0129, AllReg: 0.0117, BotRReg: 0.0167, OV: 0.9147, AltV: 0.9272, CorV: 0.9116, TopV: 0.9133, BotRV: 0.9095, AllV: 0.9272
96
+ [2026-02-20T15:12:24.959095Z] Loop 79: Reg: 0.0040, AltReg: 0.0123, CorReg: 0.0019, TopReg: 0.0136, AllReg: 0.0123, BotRReg: 0.0177, OV: 0.9146, AltV: 0.9267, CorV: 0.9117, TopV: 0.9126, BotRV: 0.9085, AllV: 0.9267
97
+ [2026-02-20T15:12:25.888869Z] Loop 80: Reg: 0.0041, AltReg: 0.0130, CorReg: 0.0019, TopReg: 0.0145, AllReg: 0.0130, BotRReg: 0.0188, OV: 0.9145, AltV: 0.9260, CorV: 0.9117, TopV: 0.9117, BotRV: 0.9075, AllV: 0.9260
98
+ [2026-02-20T15:37:36.308908Z] Loop 0: Reg: 0.0043, AltReg: 0.0129, CorReg: 0.0022, TopReg: 0.0136, AllReg: 0.0129, BotRReg: 0.0152, OV: 0.9143, AltV: 0.9260, CorV: 0.9114, TopV: 0.9127, BotRV: 0.9110, AllV: 0.9260
99
+ [2026-02-20T15:37:37.347734Z] Loop 1: Reg: 0.0051, AltReg: 0.0172, CorReg: 0.0022, TopReg: 0.0172, AllReg: 0.0172, BotRReg: 0.0233, OV: 0.9135, AltV: 0.9217, CorV: 0.9115, TopV: 0.9090, BotRV: 0.9029, AllV: 0.9217
100
+ [2026-02-20T15:37:38.276302Z] Loop 2: Reg: 0.0050, AltReg: 0.0161, CorReg: 0.0023, TopReg: 0.0161, AllReg: 0.0161, BotRReg: 0.0207, OV: 0.9136, AltV: 0.9229, CorV: 0.9114, TopV: 0.9101, BotRV: 0.9055, AllV: 0.9229
101
+ [2026-02-20T15:37:39.204915Z] Loop 3: Reg: 0.0056, AltReg: 0.0170, CorReg: 0.0028, TopReg: 0.0168, AllReg: 0.0170, BotRReg: 0.0188, OV: 0.9130, AltV: 0.9220, CorV: 0.9108, TopV: 0.9094, BotRV: 0.9074, AllV: 0.9220
102
+ [2026-02-20T15:37:40.131859Z] Loop 4: Reg: 0.0074, AltReg: 0.0204, CorReg: 0.0042, TopReg: 0.0202, AllReg: 0.0204, BotRReg: 0.0180, OV: 0.9112, AltV: 0.9186, CorV: 0.9094, TopV: 0.9060, BotRV: 0.9082, AllV: 0.9186
103
+ [2026-02-20T15:37:41.054487Z] Loop 5: Reg: 0.0097, AltReg: 0.0245, CorReg: 0.0061, TopReg: 0.0245, AllReg: 0.0245, BotRReg: 0.0186, OV: 0.9089, AltV: 0.9144, CorV: 0.9075, TopV: 0.9018, BotRV: 0.9076, AllV: 0.9144
104
+ [2026-02-20T15:37:41.982232Z] Loop 6: Reg: 0.0081, AltReg: 0.0216, CorReg: 0.0048, TopReg: 0.0216, AllReg: 0.0216, BotRReg: 0.0178, OV: 0.9105, AltV: 0.9174, CorV: 0.9089, TopV: 0.9046, BotRV: 0.9084, AllV: 0.9174
105
+ [2026-02-20T15:37:42.910203Z] Loop 7: Reg: 0.0069, AltReg: 0.0195, CorReg: 0.0039, TopReg: 0.0191, AllReg: 0.0195, BotRReg: 0.0182, OV: 0.9117, AltV: 0.9195, CorV: 0.9098, TopV: 0.9071, BotRV: 0.9080, AllV: 0.9195
106
+ [2026-02-20T15:37:43.836508Z] Loop 8: Reg: 0.0059, AltReg: 0.0172, CorReg: 0.0031, TopReg: 0.0167, AllReg: 0.0172, BotRReg: 0.0175, OV: 0.9127, AltV: 0.9217, CorV: 0.9105, TopV: 0.9095, BotRV: 0.9087, AllV: 0.9217
107
+ [2026-02-20T15:37:44.764907Z] Loop 9: Reg: 0.0049, AltReg: 0.0149, CorReg: 0.0024, TopReg: 0.0143, AllReg: 0.0149, BotRReg: 0.0169, OV: 0.9137, AltV: 0.9240, CorV: 0.9112, TopV: 0.9119, BotRV: 0.9093, AllV: 0.9240
108
+ [2026-02-20T15:37:45.692123Z] Loop 10: Reg: 0.0044, AltReg: 0.0134, CorReg: 0.0022, TopReg: 0.0130, AllReg: 0.0134, BotRReg: 0.0162, OV: 0.9142, AltV: 0.9256, CorV: 0.9115, TopV: 0.9132, BotRV: 0.9100, AllV: 0.9256
109
+ [2026-02-20T15:37:46.615275Z] Loop 11: Reg: 0.0042, AltReg: 0.0129, CorReg: 0.0021, TopReg: 0.0126, AllReg: 0.0129, BotRReg: 0.0162, OV: 0.9144, AltV: 0.9261, CorV: 0.9115, TopV: 0.9136, BotRV: 0.9100, AllV: 0.9261
110
+ [2026-02-20T15:37:47.538972Z] Loop 12: Reg: 0.0042, AltReg: 0.0126, CorReg: 0.0021, TopReg: 0.0123, AllReg: 0.0126, BotRReg: 0.0167, OV: 0.9145, AltV: 0.9263, CorV: 0.9116, TopV: 0.9139, BotRV: 0.9095, AllV: 0.9263
111
+ [2026-02-20T15:37:48.463773Z] Loop 13: Reg: 0.0041, AltReg: 0.0127, CorReg: 0.0020, TopReg: 0.0122, AllReg: 0.0127, BotRReg: 0.0177, OV: 0.9145, AltV: 0.9263, CorV: 0.9116, TopV: 0.9140, BotRV: 0.9085, AllV: 0.9263
112
+ [2026-02-20T15:37:49.388327Z] Loop 14: Reg: 0.0042, AltReg: 0.0132, CorReg: 0.0020, TopReg: 0.0124, AllReg: 0.0132, BotRReg: 0.0197, OV: 0.9144, AltV: 0.9258, CorV: 0.9116, TopV: 0.9138, BotRV: 0.9065, AllV: 0.9258
113
+ [2026-02-20T15:37:50.315289Z] Loop 15: Reg: 0.0045, AltReg: 0.0152, CorReg: 0.0019, TopReg: 0.0133, AllReg: 0.0152, BotRReg: 0.0233, OV: 0.9141, AltV: 0.9238, CorV: 0.9117, TopV: 0.9129, BotRV: 0.9029, AllV: 0.9238
114
+ [2026-02-20T15:37:51.243077Z] Loop 16: Reg: 0.0052, AltReg: 0.0184, CorReg: 0.0019, TopReg: 0.0148, AllReg: 0.0184, BotRReg: 0.0281, OV: 0.9135, AltV: 0.9205, CorV: 0.9117, TopV: 0.9114, BotRV: 0.8981, AllV: 0.9205
115
+ [2026-02-20T15:37:52.172412Z] Loop 17: Reg: 0.0053, AltReg: 0.0189, CorReg: 0.0019, TopReg: 0.0148, AllReg: 0.0189, BotRReg: 0.0290, OV: 0.9134, AltV: 0.9201, CorV: 0.9117, TopV: 0.9114, BotRV: 0.8972, AllV: 0.9201
116
+ [2026-02-20T15:37:53.099050Z] Loop 18: Reg: 0.0051, AltReg: 0.0180, CorReg: 0.0019, TopReg: 0.0143, AllReg: 0.0180, BotRReg: 0.0283, OV: 0.9135, AltV: 0.9209, CorV: 0.9117, TopV: 0.9120, BotRV: 0.8979, AllV: 0.9209
117
+ [2026-02-20T15:37:54.028028Z] Loop 19: Reg: 0.0049, AltReg: 0.0170, CorReg: 0.0020, TopReg: 0.0136, AllReg: 0.0170, BotRReg: 0.0272, OV: 0.9137, AltV: 0.9220, CorV: 0.9117, TopV: 0.9126, BotRV: 0.8990, AllV: 0.9220
118
+ [2026-02-20T15:37:54.957200Z] Loop 20: Reg: 0.0049, AltReg: 0.0170, CorReg: 0.0020, TopReg: 0.0133, AllReg: 0.0170, BotRReg: 0.0277, OV: 0.9137, AltV: 0.9220, CorV: 0.9116, TopV: 0.9129, BotRV: 0.8985, AllV: 0.9220
119
+ [2026-02-20T15:37:55.886296Z] Loop 21: Reg: 0.0049, AltReg: 0.0167, CorReg: 0.0020, TopReg: 0.0131, AllReg: 0.0167, BotRReg: 0.0275, OV: 0.9137, AltV: 0.9223, CorV: 0.9116, TopV: 0.9131, BotRV: 0.8987, AllV: 0.9223
120
+ [2026-02-20T15:37:56.813803Z] Loop 22: Reg: 0.0048, AltReg: 0.0162, CorReg: 0.0020, TopReg: 0.0130, AllReg: 0.0162, BotRReg: 0.0272, OV: 0.9138, AltV: 0.9228, CorV: 0.9116, TopV: 0.9132, BotRV: 0.8990, AllV: 0.9228
121
+ [2026-02-20T15:37:57.745386Z] Loop 23: Reg: 0.0047, AltReg: 0.0154, CorReg: 0.0021, TopReg: 0.0128, AllReg: 0.0154, BotRReg: 0.0265, OV: 0.9139, AltV: 0.9235, CorV: 0.9116, TopV: 0.9134, BotRV: 0.8997, AllV: 0.9235
122
+ [2026-02-20T15:37:58.677212Z] Loop 24: Reg: 0.0047, AltReg: 0.0151, CorReg: 0.0022, TopReg: 0.0128, AllReg: 0.0151, BotRReg: 0.0265, OV: 0.9139, AltV: 0.9239, CorV: 0.9115, TopV: 0.9134, BotRV: 0.8997, AllV: 0.9239
123
+ [2026-02-20T15:37:59.607830Z] Loop 25: Reg: 0.0049, AltReg: 0.0156, CorReg: 0.0023, TopReg: 0.0136, AllReg: 0.0156, BotRReg: 0.0276, OV: 0.9137, AltV: 0.9234, CorV: 0.9113, TopV: 0.9126, BotRV: 0.8986, AllV: 0.9234
124
+ [2026-02-20T15:38:00.539546Z] Loop 26: Reg: 0.0055, AltReg: 0.0180, CorReg: 0.0025, TopReg: 0.0163, AllReg: 0.0180, BotRReg: 0.0304, OV: 0.9131, AltV: 0.9210, CorV: 0.9111, TopV: 0.9099, BotRV: 0.8958, AllV: 0.9210
125
+ [2026-02-20T15:38:01.470737Z] Loop 27: Reg: 0.0060, AltReg: 0.0201, CorReg: 0.0025, TopReg: 0.0177, AllReg: 0.0201, BotRReg: 0.0339, OV: 0.9126, AltV: 0.9188, CorV: 0.9111, TopV: 0.9085, BotRV: 0.8923, AllV: 0.9188
126
+ [2026-02-20T15:38:02.402032Z] Loop 28: Reg: 0.0062, AltReg: 0.0206, CorReg: 0.0027, TopReg: 0.0187, AllReg: 0.0206, BotRReg: 0.0329, OV: 0.9124, AltV: 0.9183, CorV: 0.9110, TopV: 0.9075, BotRV: 0.8933, AllV: 0.9183
127
+ [2026-02-20T15:38:03.331737Z] Loop 29: Reg: 0.0065, AltReg: 0.0223, CorReg: 0.0026, TopReg: 0.0207, AllReg: 0.0223, BotRReg: 0.0344, OV: 0.9121, AltV: 0.9167, CorV: 0.9110, TopV: 0.9055, BotRV: 0.8918, AllV: 0.9167
128
+ [2026-02-20T15:38:04.259922Z] Loop 30: Reg: 0.0063, AltReg: 0.0216, CorReg: 0.0026, TopReg: 0.0206, AllReg: 0.0216, BotRReg: 0.0332, OV: 0.9123, AltV: 0.9174, CorV: 0.9111, TopV: 0.9056, BotRV: 0.8930, AllV: 0.9174
129
+ [2026-02-20T15:38:05.185151Z] Loop 31: Reg: 0.0063, AltReg: 0.0219, CorReg: 0.0025, TopReg: 0.0206, AllReg: 0.0219, BotRReg: 0.0349, OV: 0.9123, AltV: 0.9171, CorV: 0.9112, TopV: 0.9056, BotRV: 0.8913, AllV: 0.9171
130
+ [2026-02-20T15:38:06.113213Z] Loop 32: Reg: 0.0062, AltReg: 0.0218, CorReg: 0.0024, TopReg: 0.0203, AllReg: 0.0218, BotRReg: 0.0353, OV: 0.9124, AltV: 0.9172, CorV: 0.9113, TopV: 0.9060, BotRV: 0.8910, AllV: 0.9172
131
+ [2026-02-20T15:38:07.044130Z] Loop 33: Reg: 0.0057, AltReg: 0.0196, CorReg: 0.0023, TopReg: 0.0188, AllReg: 0.0196, BotRReg: 0.0314, OV: 0.9129, AltV: 0.9194, CorV: 0.9113, TopV: 0.9074, BotRV: 0.8948, AllV: 0.9194
132
+ [2026-02-20T15:38:07.975725Z] Loop 34: Reg: 0.0053, AltReg: 0.0177, CorReg: 0.0023, TopReg: 0.0175, AllReg: 0.0177, BotRReg: 0.0280, OV: 0.9133, AltV: 0.9213, CorV: 0.9114, TopV: 0.9087, BotRV: 0.8982, AllV: 0.9213
133
+ [2026-02-20T15:38:08.902937Z] Loop 35: Reg: 0.0049, AltReg: 0.0155, CorReg: 0.0023, TopReg: 0.0159, AllReg: 0.0155, BotRReg: 0.0237, OV: 0.9137, AltV: 0.9234, CorV: 0.9113, TopV: 0.9103, BotRV: 0.9025, AllV: 0.9234
134
+ [2026-02-20T15:38:09.829330Z] Loop 36: Reg: 0.0047, AltReg: 0.0140, CorReg: 0.0024, TopReg: 0.0148, AllReg: 0.0140, BotRReg: 0.0205, OV: 0.9140, AltV: 0.9249, CorV: 0.9113, TopV: 0.9114, BotRV: 0.9058, AllV: 0.9249
135
+ [2026-02-20T15:38:10.757584Z] Loop 37: Reg: 0.0045, AltReg: 0.0130, CorReg: 0.0024, TopReg: 0.0141, AllReg: 0.0130, BotRReg: 0.0175, OV: 0.9141, AltV: 0.9259, CorV: 0.9112, TopV: 0.9121, BotRV: 0.9087, AllV: 0.9259
136
+ [2026-02-20T15:38:11.706585Z] Loop 38: Reg: 0.0044, AltReg: 0.0128, CorReg: 0.0024, TopReg: 0.0140, AllReg: 0.0128, BotRReg: 0.0163, OV: 0.9142, AltV: 0.9261, CorV: 0.9113, TopV: 0.9122, BotRV: 0.9099, AllV: 0.9261
137
+ [2026-02-20T15:38:12.797860Z] Loop 39: Reg: 0.0044, AltReg: 0.0128, CorReg: 0.0024, TopReg: 0.0139, AllReg: 0.0128, BotRReg: 0.0159, OV: 0.9142, AltV: 0.9262, CorV: 0.9113, TopV: 0.9123, BotRV: 0.9103, AllV: 0.9262
138
+ [2026-02-20T15:38:14.448622Z] Loop 40: Reg: 0.0044, AltReg: 0.0128, CorReg: 0.0023, TopReg: 0.0139, AllReg: 0.0128, BotRReg: 0.0158, OV: 0.9142, AltV: 0.9262, CorV: 0.9113, TopV: 0.9124, BotRV: 0.9104, AllV: 0.9262
139
+ [2026-02-20T15:38:15.489053Z] Loop 41: Reg: 0.0043, AltReg: 0.0127, CorReg: 0.0023, TopReg: 0.0137, AllReg: 0.0127, BotRReg: 0.0160, OV: 0.9143, AltV: 0.9263, CorV: 0.9114, TopV: 0.9126, BotRV: 0.9102, AllV: 0.9263
140
+ [2026-02-20T15:38:17.298066Z] Loop 42: Reg: 0.0042, AltReg: 0.0125, CorReg: 0.0022, TopReg: 0.0133, AllReg: 0.0125, BotRReg: 0.0165, OV: 0.9144, AltV: 0.9264, CorV: 0.9115, TopV: 0.9129, BotRV: 0.9097, AllV: 0.9264
141
+ [2026-02-20T15:38:18.993085Z] Loop 43: Reg: 0.0042, AltReg: 0.0126, CorReg: 0.0021, TopReg: 0.0130, AllReg: 0.0126, BotRReg: 0.0175, OV: 0.9145, AltV: 0.9264, CorV: 0.9115, TopV: 0.9132, BotRV: 0.9087, AllV: 0.9264
142
+ [2026-02-20T15:38:20.007401Z] Loop 44: Reg: 0.0041, AltReg: 0.0129, CorReg: 0.0020, TopReg: 0.0127, AllReg: 0.0129, BotRReg: 0.0190, OV: 0.9145, AltV: 0.9261, CorV: 0.9117, TopV: 0.9135, BotRV: 0.9073, AllV: 0.9261
143
+ [2026-02-20T15:38:21.706251Z] Loop 45: Reg: 0.0042, AltReg: 0.0138, CorReg: 0.0019, TopReg: 0.0128, AllReg: 0.0138, BotRReg: 0.0206, OV: 0.9144, AltV: 0.9251, CorV: 0.9117, TopV: 0.9134, BotRV: 0.9056, AllV: 0.9251
144
+ [2026-02-20T15:38:23.595350Z] Loop 46: Reg: 0.0045, AltReg: 0.0153, CorReg: 0.0018, TopReg: 0.0131, AllReg: 0.0153, BotRReg: 0.0226, OV: 0.9141, AltV: 0.9236, CorV: 0.9118, TopV: 0.9131, BotRV: 0.9036, AllV: 0.9236
145
+ [2026-02-20T15:38:25.065027Z] Loop 47: Reg: 0.0048, AltReg: 0.0170, CorReg: 0.0018, TopReg: 0.0138, AllReg: 0.0170, BotRReg: 0.0246, OV: 0.9138, AltV: 0.9220, CorV: 0.9119, TopV: 0.9124, BotRV: 0.9016, AllV: 0.9220
146
+ [2026-02-20T15:38:25.994508Z] Loop 48: Reg: 0.0051, AltReg: 0.0188, CorReg: 0.0018, TopReg: 0.0144, AllReg: 0.0188, BotRReg: 0.0262, OV: 0.9135, AltV: 0.9201, CorV: 0.9119, TopV: 0.9118, BotRV: 0.9000, AllV: 0.9201
147
+ [2026-02-20T15:38:26.922053Z] Loop 49: Reg: 0.0057, AltReg: 0.0220, CorReg: 0.0017, TopReg: 0.0153, AllReg: 0.0220, BotRReg: 0.0282, OV: 0.9129, AltV: 0.9169, CorV: 0.9119, TopV: 0.9109, BotRV: 0.8980, AllV: 0.9169
148
+ [2026-02-20T15:38:27.848985Z] Loop 50: Reg: 0.0056, AltReg: 0.0216, CorReg: 0.0017, TopReg: 0.0150, AllReg: 0.0216, BotRReg: 0.0274, OV: 0.9130, AltV: 0.9174, CorV: 0.9119, TopV: 0.9113, BotRV: 0.8988, AllV: 0.9174
149
+ [2026-02-20T15:38:28.778076Z] Loop 51: Reg: 0.0055, AltReg: 0.0206, CorReg: 0.0017, TopReg: 0.0147, AllReg: 0.0206, BotRReg: 0.0262, OV: 0.9132, AltV: 0.9183, CorV: 0.9119, TopV: 0.9115, BotRV: 0.9000, AllV: 0.9183
150
+ [2026-02-20T15:38:29.704483Z] Loop 52: Reg: 0.0051, AltReg: 0.0189, CorReg: 0.0018, TopReg: 0.0145, AllReg: 0.0189, BotRReg: 0.0244, OV: 0.9135, AltV: 0.9201, CorV: 0.9119, TopV: 0.9117, BotRV: 0.9018, AllV: 0.9201
151
+ [2026-02-20T15:38:30.635891Z] Loop 53: Reg: 0.0048, AltReg: 0.0168, CorReg: 0.0018, TopReg: 0.0149, AllReg: 0.0168, BotRReg: 0.0222, OV: 0.9139, AltV: 0.9222, CorV: 0.9118, TopV: 0.9114, BotRV: 0.9041, AllV: 0.9222
152
+ [2026-02-20T15:38:31.566407Z] Loop 54: Reg: 0.0046, AltReg: 0.0155, CorReg: 0.0019, TopReg: 0.0155, AllReg: 0.0155, BotRReg: 0.0205, OV: 0.9141, AltV: 0.9235, CorV: 0.9118, TopV: 0.9107, BotRV: 0.9057, AllV: 0.9235
153
+ [2026-02-20T15:38:32.496598Z] Loop 55: Reg: 0.0046, AltReg: 0.0153, CorReg: 0.0020, TopReg: 0.0171, AllReg: 0.0153, BotRReg: 0.0196, OV: 0.9140, AltV: 0.9237, CorV: 0.9117, TopV: 0.9091, BotRV: 0.9067, AllV: 0.9237
154
+ [2026-02-20T15:38:33.426606Z] Loop 56: Reg: 0.0048, AltReg: 0.0161, CorReg: 0.0021, TopReg: 0.0191, AllReg: 0.0161, BotRReg: 0.0198, OV: 0.9138, AltV: 0.9228, CorV: 0.9116, TopV: 0.9071, BotRV: 0.9065, AllV: 0.9228
155
+ [2026-02-20T15:38:34.356557Z] Loop 57: Reg: 0.0049, AltReg: 0.0163, CorReg: 0.0021, TopReg: 0.0193, AllReg: 0.0163, BotRReg: 0.0200, OV: 0.9137, AltV: 0.9226, CorV: 0.9115, TopV: 0.9069, BotRV: 0.9062, AllV: 0.9226
156
+ [2026-02-20T15:38:35.285129Z] Loop 58: Reg: 0.0049, AltReg: 0.0163, CorReg: 0.0021, TopReg: 0.0184, AllReg: 0.0163, BotRReg: 0.0204, OV: 0.9138, AltV: 0.9226, CorV: 0.9116, TopV: 0.9078, BotRV: 0.9058, AllV: 0.9226
157
+ [2026-02-20T15:38:36.214200Z] Loop 59: Reg: 0.0047, AltReg: 0.0154, CorReg: 0.0020, TopReg: 0.0166, AllReg: 0.0154, BotRReg: 0.0199, OV: 0.9140, AltV: 0.9236, CorV: 0.9116, TopV: 0.9096, BotRV: 0.9063, AllV: 0.9236
158
+ [2026-02-20T15:38:37.138567Z] Loop 60: Reg: 0.0045, AltReg: 0.0147, CorReg: 0.0020, TopReg: 0.0156, AllReg: 0.0147, BotRReg: 0.0195, OV: 0.9141, AltV: 0.9243, CorV: 0.9116, TopV: 0.9106, BotRV: 0.9067, AllV: 0.9243
159
+ [2026-02-20T15:38:38.063793Z] Loop 61: Reg: 0.0044, AltReg: 0.0140, CorReg: 0.0021, TopReg: 0.0150, AllReg: 0.0140, BotRReg: 0.0185, OV: 0.9142, AltV: 0.9250, CorV: 0.9115, TopV: 0.9112, BotRV: 0.9077, AllV: 0.9250
160
+ [2026-02-20T15:38:38.988889Z] Loop 62: Reg: 0.0044, AltReg: 0.0136, CorReg: 0.0021, TopReg: 0.0147, AllReg: 0.0136, BotRReg: 0.0180, OV: 0.9142, AltV: 0.9253, CorV: 0.9115, TopV: 0.9116, BotRV: 0.9083, AllV: 0.9253
161
+ [2026-02-20T15:38:39.914429Z] Loop 63: Reg: 0.0043, AltReg: 0.0132, CorReg: 0.0022, TopReg: 0.0142, AllReg: 0.0132, BotRReg: 0.0175, OV: 0.9143, AltV: 0.9257, CorV: 0.9115, TopV: 0.9121, BotRV: 0.9087, AllV: 0.9257
162
+ [2026-02-20T15:38:40.841271Z] Loop 64: Reg: 0.0043, AltReg: 0.0129, CorReg: 0.0021, TopReg: 0.0135, AllReg: 0.0129, BotRReg: 0.0174, OV: 0.9144, AltV: 0.9261, CorV: 0.9115, TopV: 0.9127, BotRV: 0.9088, AllV: 0.9261
163
+ [2026-02-20T15:38:41.767823Z] Loop 65: Reg: 0.0042, AltReg: 0.0127, CorReg: 0.0021, TopReg: 0.0130, AllReg: 0.0127, BotRReg: 0.0173, OV: 0.9144, AltV: 0.9263, CorV: 0.9115, TopV: 0.9132, BotRV: 0.9089, AllV: 0.9263
164
+ [2026-02-20T15:38:42.693625Z] Loop 66: Reg: 0.0042, AltReg: 0.0129, CorReg: 0.0021, TopReg: 0.0130, AllReg: 0.0129, BotRReg: 0.0180, OV: 0.9144, AltV: 0.9260, CorV: 0.9116, TopV: 0.9132, BotRV: 0.9082, AllV: 0.9260
165
+ [2026-02-20T15:38:43.619395Z] Loop 67: Reg: 0.0043, AltReg: 0.0138, CorReg: 0.0020, TopReg: 0.0134, AllReg: 0.0138, BotRReg: 0.0197, OV: 0.9143, AltV: 0.9252, CorV: 0.9116, TopV: 0.9128, BotRV: 0.9065, AllV: 0.9252
166
+ [2026-02-20T15:38:44.548501Z] Loop 68: Reg: 0.0045, AltReg: 0.0151, CorReg: 0.0020, TopReg: 0.0139, AllReg: 0.0151, BotRReg: 0.0216, OV: 0.9141, AltV: 0.9239, CorV: 0.9117, TopV: 0.9123, BotRV: 0.9046, AllV: 0.9239
167
+ [2026-02-20T15:38:45.476538Z] Loop 69: Reg: 0.0048, AltReg: 0.0163, CorReg: 0.0019, TopReg: 0.0143, AllReg: 0.0163, BotRReg: 0.0233, OV: 0.9139, AltV: 0.9227, CorV: 0.9117, TopV: 0.9119, BotRV: 0.9029, AllV: 0.9227
168
+ [2026-02-20T15:38:46.404170Z] Loop 70: Reg: 0.0047, AltReg: 0.0161, CorReg: 0.0019, TopReg: 0.0140, AllReg: 0.0161, BotRReg: 0.0234, OV: 0.9139, AltV: 0.9228, CorV: 0.9117, TopV: 0.9122, BotRV: 0.9028, AllV: 0.9228
169
+ [2026-02-20T15:38:47.330451Z] Loop 71: Reg: 0.0046, AltReg: 0.0155, CorReg: 0.0019, TopReg: 0.0134, AllReg: 0.0155, BotRReg: 0.0229, OV: 0.9140, AltV: 0.9234, CorV: 0.9117, TopV: 0.9128, BotRV: 0.9033, AllV: 0.9234
170
+ [2026-02-20T15:38:48.259462Z] Loop 72: Reg: 0.0046, AltReg: 0.0155, CorReg: 0.0019, TopReg: 0.0130, AllReg: 0.0155, BotRReg: 0.0231, OV: 0.9141, AltV: 0.9235, CorV: 0.9118, TopV: 0.9132, BotRV: 0.9031, AllV: 0.9235
171
+ [2026-02-20T15:38:49.188147Z] Loop 73: Reg: 0.0045, AltReg: 0.0150, CorReg: 0.0019, TopReg: 0.0129, AllReg: 0.0150, BotRReg: 0.0227, OV: 0.9142, AltV: 0.9239, CorV: 0.9118, TopV: 0.9133, BotRV: 0.9036, AllV: 0.9239
172
+ [2026-02-20T15:38:50.115884Z] Loop 74: Reg: 0.0043, AltReg: 0.0142, CorReg: 0.0019, TopReg: 0.0129, AllReg: 0.0142, BotRReg: 0.0214, OV: 0.9143, AltV: 0.9247, CorV: 0.9118, TopV: 0.9133, BotRV: 0.9048, AllV: 0.9247
173
+ [2026-02-20T15:38:51.044619Z] Loop 75: Reg: 0.0041, AltReg: 0.0130, CorReg: 0.0019, TopReg: 0.0128, AllReg: 0.0130, BotRReg: 0.0194, OV: 0.9145, AltV: 0.9259, CorV: 0.9117, TopV: 0.9134, BotRV: 0.9068, AllV: 0.9259
174
+ [2026-02-20T15:38:51.971689Z] Loop 76: Reg: 0.0040, AltReg: 0.0123, CorReg: 0.0020, TopReg: 0.0127, AllReg: 0.0123, BotRReg: 0.0182, OV: 0.9146, AltV: 0.9266, CorV: 0.9117, TopV: 0.9135, BotRV: 0.9081, AllV: 0.9266
175
+ [2026-02-20T15:38:52.904313Z] Loop 77: Reg: 0.0039, AltReg: 0.0119, CorReg: 0.0020, TopReg: 0.0127, AllReg: 0.0119, BotRReg: 0.0173, OV: 0.9147, AltV: 0.9270, CorV: 0.9117, TopV: 0.9135, BotRV: 0.9089, AllV: 0.9270
176
+ [2026-02-20T15:38:53.836127Z] Loop 78: Reg: 0.0039, AltReg: 0.0117, CorReg: 0.0020, TopReg: 0.0129, AllReg: 0.0117, BotRReg: 0.0167, OV: 0.9147, AltV: 0.9272, CorV: 0.9116, TopV: 0.9133, BotRV: 0.9095, AllV: 0.9272
177
+ [2026-02-20T15:38:54.767295Z] Loop 79: Reg: 0.0040, AltReg: 0.0123, CorReg: 0.0019, TopReg: 0.0136, AllReg: 0.0123, BotRReg: 0.0177, OV: 0.9146, AltV: 0.9267, CorV: 0.9117, TopV: 0.9126, BotRV: 0.9085, AllV: 0.9267
178
+ [2026-02-20T15:38:55.697130Z] Loop 80: Reg: 0.0041, AltReg: 0.0130, CorReg: 0.0019, TopReg: 0.0145, AllReg: 0.0130, BotRReg: 0.0188, OV: 0.9145, AltV: 0.9260, CorV: 0.9117, TopV: 0.9117, BotRV: 0.9075, AllV: 0.9260
al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0/latest_train.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "ts": "2026-02-20T15:38:55.751047Z",
3
+ "loop": 80,
4
+ "env_steps": 49766399,
5
+ "loss": 0.04076342284679413,
6
+ "avg_return": 0.9136733412742615,
7
+ "regret": 0.004086306784301996,
8
+ "entropy": 0.15896055102348328,
9
+ "lr": 5e-05,
10
+ "discount_rate": 0.99,
11
+ "num_rollout_steps": 64
12
+ }
al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0/patterning.log ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ============================================================
2
+ Patterning config summary
3
+ ============================================================
4
+ patt_mode: diff
5
+ patt_h: -0.8
6
+ alpha: 0.1966666666666666
7
+ model_id: al_0.6_g_0.98_id_17_seed_980617
8
+ resume: jaxgmg2_3phase_optim_state/al_0.6_g_0.98_id_17_seed_980617
9
+ resume_id: 3810
10
+ resume_optim: False
11
+ ckpt_path: jaxgmg2_3phase_optim_state_patt/al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0
12
+ smoke: False
13
+ ============================================================
14
+ ============================================================
15
+ Patterning config summary
16
+ ============================================================
17
+ patt_mode: diff
18
+ patt_h: -0.8
19
+ alpha: 0.1966666666666666
20
+ model_id: al_0.6_g_0.98_id_17_seed_980617
21
+ resume: jaxgmg2_3phase_optim_state/al_0.6_g_0.98_id_17_seed_980617
22
+ resume_id: 3810
23
+ resume_optim: False
24
+ ckpt_path: jaxgmg2_3phase_optim_state_patt/al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0
25
+ smoke: False
26
+ ============================================================
27
+ ============================================================
28
+ Patterning config summary
29
+ ============================================================
30
+ patt_mode: diff
31
+ patt_h: -0.8
32
+ alpha: 0.1966666666666666
33
+ model_id: al_0.6_g_0.98_id_17_seed_980617
34
+ resume: jaxgmg2_3phase_optim_state/al_0.6_g_0.98_id_17_seed_980617
35
+ resume_id: 3810
36
+ resume_optim: False
37
+ ckpt_path: jaxgmg2_3phase_optim_state_patt/al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0
38
+ smoke: False
39
+ ============================================================
40
+ ============================================================
41
+ Patterning config summary
42
+ ============================================================
43
+ patt_mode: diff
44
+ patt_h: -0.8
45
+ alpha: 0.1966666666666666
46
+ model_id: al_0.6_g_0.98_id_17_seed_980617
47
+ resume: jaxgmg2_3phase_optim_state/al_0.6_g_0.98_id_17_seed_980617
48
+ resume_id: 3810
49
+ resume_optim: False
50
+ ckpt_path: jaxgmg2_3phase_optim_state_patt/al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0
51
+ smoke: False
52
+ ============================================================
al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0/setup.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "rl_action": "train",
4
+ "model_type": "impala",
5
+ "lr": 5e-05,
6
+ "discount_rate": 0.99,
7
+ "num_rollout_steps": 64,
8
+ "grad_acc_per_chunk": 4,
9
+ "num_rollout_chunks": 1,
10
+ "cheese_loc": "any",
11
+ "env_layout": "open",
12
+ "alpha": 0.1966666666666666,
13
+ "env_size": 13,
14
+ "num_levels": 9600,
15
+ "compile": true,
16
+ "use_prev_action": false,
17
+ "weight_restrictions": null,
18
+ "weight_restrictions_invert": false,
19
+ "use_bf16": false,
20
+ "use_wandb": true,
21
+ "seed": 42,
22
+ "mask_type": "first_episode",
23
+ "ckpt_dir": "jaxgmg2_3phase_optim_state_patt",
24
+ "vis_average_state": false,
25
+ "trim_episodes": false,
26
+ "num_total_env_steps": 50000000,
27
+ "eval_every": 1,
28
+ "eff_horizon": null,
29
+ "optim": "adam",
30
+ "env_rule": null,
31
+ "use_hf": true,
32
+ "use_log": true,
33
+ "log_optimizer_state": false,
34
+ "resume": "jaxgmg2_3phase_optim_state/al_0.6_g_0.98_id_17_seed_980617",
35
+ "resume_id": 3810,
36
+ "resume_optim": false,
37
+ "checkpoint": "al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0",
38
+ "wandb_project": "jaxgmg_test",
39
+ "eval_schedule": "0:1",
40
+ "render_sixel": false,
41
+ "sixel_idx": 60,
42
+ "live_monitor": false,
43
+ "run_id": 0,
44
+ "seed_formula": null,
45
+ "deterministic": true,
46
+ "penalize_time": false,
47
+ "f_str_ckpt": null,
48
+ "duplication_factor": -1,
49
+ "smoke": false,
50
+ "ntfy": null,
51
+ "num_chains": 6,
52
+ "num_draws": 3000,
53
+ "num_steps_bw_draws": 1,
54
+ "on_policy": true,
55
+ "llc_nbeta": 3000,
56
+ "localization": 10,
57
+ "exact_solver_each_draw": false,
58
+ "llc_optimizer": "sgld",
59
+ "iw_clip_eps": null,
60
+ "rmsprop_burnin_steps": 20,
61
+ "llc_data_file": "llc_scan_open_reinforce.pkl",
62
+ "llc_checkpoint_index": null,
63
+ "llc_checkpoint_number": null,
64
+ "sink": null,
65
+ "repo_id": "davidquarel/jaxgmg_ckpt_zip",
66
+ "use_shuffled_checkpoints": false,
67
+ "force_re_download": false,
68
+ "off_distribution_data": false,
69
+ "evaluate_every_position": false,
70
+ "num_prev_actions": 1,
71
+ "eff_acc_steps": 4,
72
+ "chunk_size": 9600,
73
+ "env_steps_per_microbatch": 153600,
74
+ "ckpt_path": "jaxgmg2_3phase_optim_state_patt/al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0",
75
+ "env_steps_per_loop": 614400,
76
+ "total_loops": 81,
77
+ "patt_mode": "diff",
78
+ "patt_h": -0.8,
79
+ "model_id": "al_0.6_g_0.98_id_17_seed_980617",
80
+ "_patt_weights": null
81
+ },
82
+ "setup": {
83
+ "start_time_utc": "2026-02-20T15:37:08.466182Z",
84
+ "seed": 42,
85
+ "device": "cuda",
86
+ "python_version": "3.11.11",
87
+ "torch_version": "2.10.0+cu128",
88
+ "jax_version": "0.6.2",
89
+ "hostname": "5a72857b6734",
90
+ "platform": "Linux-5.15.0-170-generic-x86_64-with-glibc2.35",
91
+ "git_sha": null,
92
+ "git_branch": null,
93
+ "use_wandb": true
94
+ }
95
+ }
al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0/setup.txt ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ Start: 2026-02-20T15:37:08.466182Z
2
+ Seed: 42
3
+ Device: cuda
4
+ Python: 3.11.11 | Torch: 2.10.0+cu128 | JAX: 0.6.2
5
+ Host: 5a72857b6734
6
+ Platform: Linux-5.15.0-170-generic-x86_64-with-glibc2.35
7
+ Git: branch=None sha=None
8
+ use_wandb: True
al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0/train.jsonl ADDED
@@ -0,0 +1,178 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"ts": "2026-02-20T15:08:15.003567Z", "loop": 0, "env_steps": 614399, "loss": 0.038459062576293945, "avg_return": 0.9144043326377869, "regret": 0.004308843053877354, "entropy": 0.14913484454154968, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
2
+ {"ts": "2026-02-20T15:08:15.930902Z", "loop": 1, "env_steps": 1228799, "loss": 0.04305032268166542, "avg_return": 0.914141058921814, "regret": 0.005145789589732885, "entropy": 0.16546086966991425, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
3
+ {"ts": "2026-02-20T15:08:16.856492Z", "loop": 2, "env_steps": 1843199, "loss": 0.042838335037231445, "avg_return": 0.9133297801017761, "regret": 0.004989685025066137, "entropy": 0.16842970252037048, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
4
+ {"ts": "2026-02-20T15:08:17.780882Z", "loop": 3, "env_steps": 2457599, "loss": 0.049289848655462265, "avg_return": 0.9130585193634033, "regret": 0.005611793138086796, "entropy": 0.18803898990154266, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
5
+ {"ts": "2026-02-20T15:08:18.705383Z", "loop": 4, "env_steps": 3071999, "loss": 0.05503948777914047, "avg_return": 0.9109735488891602, "regret": 0.007410373538732529, "entropy": 0.21352212131023407, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
6
+ {"ts": "2026-02-20T15:08:19.629502Z", "loop": 5, "env_steps": 3686399, "loss": 0.05555526912212372, "avg_return": 0.9085718989372253, "regret": 0.009732013568282127, "entropy": 0.22367124259471893, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
7
+ {"ts": "2026-02-20T15:08:20.552817Z", "loop": 6, "env_steps": 4300799, "loss": 0.05597533658146858, "avg_return": 0.9098407030105591, "regret": 0.0080783162266016, "entropy": 0.2134706676006317, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
8
+ {"ts": "2026-02-20T15:08:21.476661Z", "loop": 7, "env_steps": 4915199, "loss": 0.05279890075325966, "avg_return": 0.912228524684906, "regret": 0.006940040271729231, "entropy": 0.20506125688552856, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
9
+ {"ts": "2026-02-20T15:08:22.402193Z", "loop": 8, "env_steps": 5529599, "loss": 0.05076589435338974, "avg_return": 0.9128298163414001, "regret": 0.005884145386517048, "entropy": 0.19164735078811646, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
10
+ {"ts": "2026-02-20T15:08:23.330566Z", "loop": 9, "env_steps": 6143999, "loss": 0.04389328137040138, "avg_return": 0.9135256409645081, "regret": 0.004890759941190481, "entropy": 0.16351893544197083, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
11
+ {"ts": "2026-02-20T15:08:24.252544Z", "loop": 10, "env_steps": 6758399, "loss": 0.03995446115732193, "avg_return": 0.9134226441383362, "regret": 0.0043883416801691055, "entropy": 0.15135043859481812, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
12
+ {"ts": "2026-02-20T15:08:25.175373Z", "loop": 11, "env_steps": 7372799, "loss": 0.03796378895640373, "avg_return": 0.9143897891044617, "regret": 0.004246285185217857, "entropy": 0.14120905101299286, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
13
+ {"ts": "2026-02-20T15:08:26.099761Z", "loop": 12, "env_steps": 7987199, "loss": 0.03703838586807251, "avg_return": 0.9139742255210876, "regret": 0.0041516912169754505, "entropy": 0.14204582571983337, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
14
+ {"ts": "2026-02-20T15:08:27.021354Z", "loop": 13, "env_steps": 8601599, "loss": 0.036254607141017914, "avg_return": 0.9146824479103088, "regret": 0.004124278202652931, "entropy": 0.14249636232852936, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
15
+ {"ts": "2026-02-20T15:08:27.945053Z", "loop": 14, "env_steps": 9215999, "loss": 0.03912505879998207, "avg_return": 0.9140971899032593, "regret": 0.004205651581287384, "entropy": 0.15343046188354492, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
16
+ {"ts": "2026-02-20T15:08:28.868489Z", "loop": 15, "env_steps": 9830399, "loss": 0.043059494346380234, "avg_return": 0.9140105247497559, "regret": 0.004545097704976797, "entropy": 0.16417203843593597, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
17
+ {"ts": "2026-02-20T15:11:11.616100Z", "loop": 0, "env_steps": 614399, "loss": 0.038459062576293945, "avg_return": 0.9144043326377869, "regret": 0.004308843053877354, "entropy": 0.14913484454154968, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
18
+ {"ts": "2026-02-20T15:11:12.548846Z", "loop": 1, "env_steps": 1228799, "loss": 0.04305032268166542, "avg_return": 0.914141058921814, "regret": 0.005145789589732885, "entropy": 0.16546086966991425, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
19
+ {"ts": "2026-02-20T15:11:13.476173Z", "loop": 2, "env_steps": 1843199, "loss": 0.042838335037231445, "avg_return": 0.9133297801017761, "regret": 0.004989685025066137, "entropy": 0.16842970252037048, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
20
+ {"ts": "2026-02-20T15:11:14.404892Z", "loop": 3, "env_steps": 2457599, "loss": 0.049289848655462265, "avg_return": 0.9130585193634033, "regret": 0.005611793138086796, "entropy": 0.18803898990154266, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
21
+ {"ts": "2026-02-20T15:11:15.333240Z", "loop": 4, "env_steps": 3071999, "loss": 0.05503948777914047, "avg_return": 0.9109735488891602, "regret": 0.007410373538732529, "entropy": 0.21352212131023407, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
22
+ {"ts": "2026-02-20T15:11:16.268221Z", "loop": 5, "env_steps": 3686399, "loss": 0.05555526912212372, "avg_return": 0.9085718989372253, "regret": 0.009732013568282127, "entropy": 0.22367124259471893, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
23
+ {"ts": "2026-02-20T15:11:17.196926Z", "loop": 6, "env_steps": 4300799, "loss": 0.05597533658146858, "avg_return": 0.9098407030105591, "regret": 0.0080783162266016, "entropy": 0.2134706676006317, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
24
+ {"ts": "2026-02-20T15:11:18.125915Z", "loop": 7, "env_steps": 4915199, "loss": 0.05279890075325966, "avg_return": 0.912228524684906, "regret": 0.006940040271729231, "entropy": 0.20506125688552856, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
25
+ {"ts": "2026-02-20T15:11:19.051290Z", "loop": 8, "env_steps": 5529599, "loss": 0.05076589435338974, "avg_return": 0.9128298163414001, "regret": 0.005884145386517048, "entropy": 0.19164735078811646, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
26
+ {"ts": "2026-02-20T15:11:19.974981Z", "loop": 9, "env_steps": 6143999, "loss": 0.04389328137040138, "avg_return": 0.9135256409645081, "regret": 0.004890759941190481, "entropy": 0.16351893544197083, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
27
+ {"ts": "2026-02-20T15:11:20.913035Z", "loop": 10, "env_steps": 6758399, "loss": 0.03995446115732193, "avg_return": 0.9134226441383362, "regret": 0.0043883416801691055, "entropy": 0.15135043859481812, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
28
+ {"ts": "2026-02-20T15:11:21.838468Z", "loop": 11, "env_steps": 7372799, "loss": 0.03796378895640373, "avg_return": 0.9143897891044617, "regret": 0.004246285185217857, "entropy": 0.14120905101299286, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
29
+ {"ts": "2026-02-20T15:11:22.761794Z", "loop": 12, "env_steps": 7987199, "loss": 0.03703838586807251, "avg_return": 0.9139742255210876, "regret": 0.0041516912169754505, "entropy": 0.14204582571983337, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
30
+ {"ts": "2026-02-20T15:11:23.686710Z", "loop": 13, "env_steps": 8601599, "loss": 0.036254607141017914, "avg_return": 0.9146824479103088, "regret": 0.004124278202652931, "entropy": 0.14249636232852936, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
31
+ {"ts": "2026-02-20T15:11:24.611920Z", "loop": 14, "env_steps": 9215999, "loss": 0.03912505879998207, "avg_return": 0.9140971899032593, "regret": 0.004205651581287384, "entropy": 0.15343046188354492, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
32
+ {"ts": "2026-02-20T15:11:25.537865Z", "loop": 15, "env_steps": 9830399, "loss": 0.043059494346380234, "avg_return": 0.9140105247497559, "regret": 0.004545097704976797, "entropy": 0.16417203843593597, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
33
+ {"ts": "2026-02-20T15:11:26.540290Z", "loop": 16, "env_steps": 10444799, "loss": 0.04881095141172409, "avg_return": 0.9127726554870605, "regret": 0.005157078616321087, "entropy": 0.1844228208065033, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
34
+ {"ts": "2026-02-20T15:11:27.478388Z", "loop": 17, "env_steps": 11059199, "loss": 0.05005049332976341, "avg_return": 0.9135828018188477, "regret": 0.005261595826596022, "entropy": 0.19199229776859283, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
35
+ {"ts": "2026-02-20T15:11:28.418594Z", "loop": 18, "env_steps": 11673599, "loss": 0.04876140505075455, "avg_return": 0.9132229089736938, "regret": 0.00511329947039485, "entropy": 0.19011464715003967, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
36
+ {"ts": "2026-02-20T15:11:29.346420Z", "loop": 19, "env_steps": 12287999, "loss": 0.04967671260237694, "avg_return": 0.9128940105438232, "regret": 0.0049299877136945724, "entropy": 0.19220764935016632, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
37
+ {"ts": "2026-02-20T15:11:30.283499Z", "loop": 20, "env_steps": 12902399, "loss": 0.05157233402132988, "avg_return": 0.9136543869972229, "regret": 0.004945225082337856, "entropy": 0.20100222527980804, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
38
+ {"ts": "2026-02-20T15:11:31.208809Z", "loop": 21, "env_steps": 13516799, "loss": 0.053730230778455734, "avg_return": 0.9133966565132141, "regret": 0.004896321799606085, "entropy": 0.2068491131067276, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
39
+ {"ts": "2026-02-20T15:11:32.133771Z", "loop": 22, "env_steps": 14131199, "loss": 0.05553211271762848, "avg_return": 0.913227379322052, "regret": 0.00482122041285038, "entropy": 0.2085137963294983, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
40
+ {"ts": "2026-02-20T15:11:33.057041Z", "loop": 23, "env_steps": 14745599, "loss": 0.05334676429629326, "avg_return": 0.9138824939727783, "regret": 0.00471537746489048, "entropy": 0.20375385880470276, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
41
+ {"ts": "2026-02-20T15:11:33.986575Z", "loop": 24, "env_steps": 15359999, "loss": 0.054690152406692505, "avg_return": 0.9141449332237244, "regret": 0.004711857531219721, "entropy": 0.20919829607009888, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
42
+ {"ts": "2026-02-20T15:11:34.922765Z", "loop": 25, "env_steps": 15974399, "loss": 0.05489712953567505, "avg_return": 0.9134702682495117, "regret": 0.004917492624372244, "entropy": 0.2113226354122162, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
43
+ {"ts": "2026-02-20T15:11:35.849311Z", "loop": 26, "env_steps": 16588799, "loss": 0.05722189322113991, "avg_return": 0.9130019545555115, "regret": 0.005538491532206535, "entropy": 0.22079502046108246, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
44
+ {"ts": "2026-02-20T15:11:36.774709Z", "loop": 27, "env_steps": 17203199, "loss": 0.05423341691493988, "avg_return": 0.9133304953575134, "regret": 0.005992687772959471, "entropy": 0.21447180211544037, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
45
+ {"ts": "2026-02-20T15:11:37.699830Z", "loop": 28, "env_steps": 17817599, "loss": 0.05511590093374252, "avg_return": 0.9116150140762329, "regret": 0.006190338637679815, "entropy": 0.21591898798942566, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
46
+ {"ts": "2026-02-20T15:11:38.625770Z", "loop": 29, "env_steps": 18431999, "loss": 0.05198509991168976, "avg_return": 0.9118152260780334, "regret": 0.006502676755189896, "entropy": 0.20928069949150085, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
47
+ {"ts": "2026-02-20T15:11:39.551905Z", "loop": 30, "env_steps": 19046399, "loss": 0.052754003554582596, "avg_return": 0.9122692346572876, "regret": 0.006323689594864845, "entropy": 0.20549479126930237, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
48
+ {"ts": "2026-02-20T15:11:40.479334Z", "loop": 31, "env_steps": 19660799, "loss": 0.052055466920137405, "avg_return": 0.9124749898910522, "regret": 0.00627649761736393, "entropy": 0.19896496832370758, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
49
+ {"ts": "2026-02-20T15:11:41.404408Z", "loop": 32, "env_steps": 20275199, "loss": 0.0507308766245842, "avg_return": 0.9116406440734863, "regret": 0.006176636554300785, "entropy": 0.2011982500553131, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
50
+ {"ts": "2026-02-20T15:11:42.331136Z", "loop": 33, "env_steps": 20889599, "loss": 0.05132613331079483, "avg_return": 0.9138214588165283, "regret": 0.0057111987844109535, "entropy": 0.19886808097362518, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
51
+ {"ts": "2026-02-20T15:11:43.256830Z", "loop": 34, "env_steps": 21503999, "loss": 0.05241093039512634, "avg_return": 0.9129173159599304, "regret": 0.005308059975504875, "entropy": 0.2036304920911789, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
52
+ {"ts": "2026-02-20T15:11:44.182862Z", "loop": 35, "env_steps": 22118399, "loss": 0.052897609770298004, "avg_return": 0.9141751527786255, "regret": 0.004898912739008665, "entropy": 0.20442193746566772, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
53
+ {"ts": "2026-02-20T15:11:45.110327Z", "loop": 36, "env_steps": 22732799, "loss": 0.05398102104663849, "avg_return": 0.913618266582489, "regret": 0.004650804214179516, "entropy": 0.21441315114498138, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
54
+ {"ts": "2026-02-20T15:11:46.036171Z", "loop": 37, "env_steps": 23347199, "loss": 0.052688565105199814, "avg_return": 0.9147119522094727, "regret": 0.004488404840230942, "entropy": 0.20510266721248627, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
55
+ {"ts": "2026-02-20T15:11:46.961494Z", "loop": 38, "env_steps": 23961599, "loss": 0.04847056418657303, "avg_return": 0.9138769507408142, "regret": 0.004431146662682295, "entropy": 0.1905696839094162, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
56
+ {"ts": "2026-02-20T15:11:47.886809Z", "loop": 39, "env_steps": 24575999, "loss": 0.047192227095365524, "avg_return": 0.9146565198898315, "regret": 0.0044012898579239845, "entropy": 0.182176873087883, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
57
+ {"ts": "2026-02-20T15:11:48.814186Z", "loop": 40, "env_steps": 25190399, "loss": 0.046322982758283615, "avg_return": 0.9141542911529541, "regret": 0.004372016526758671, "entropy": 0.18115457892417908, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
58
+ {"ts": "2026-02-20T15:11:49.741772Z", "loop": 41, "env_steps": 25804799, "loss": 0.04591471701860428, "avg_return": 0.914177656173706, "regret": 0.004312243312597275, "entropy": 0.17777203023433685, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
59
+ {"ts": "2026-02-20T15:11:50.668009Z", "loop": 42, "env_steps": 26419199, "loss": 0.04703698679804802, "avg_return": 0.9138143062591553, "regret": 0.004224626813083887, "entropy": 0.1886642575263977, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
60
+ {"ts": "2026-02-20T15:11:51.594798Z", "loop": 43, "env_steps": 27033599, "loss": 0.050354450941085815, "avg_return": 0.9139518737792969, "regret": 0.004152423236519098, "entropy": 0.1983119547367096, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
61
+ {"ts": "2026-02-20T15:11:52.521976Z", "loop": 44, "env_steps": 27647999, "loss": 0.050561774522066116, "avg_return": 0.9143680930137634, "regret": 0.004134788177907467, "entropy": 0.1951211839914322, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
62
+ {"ts": "2026-02-20T15:11:53.447826Z", "loop": 45, "env_steps": 28262399, "loss": 0.05251600593328476, "avg_return": 0.9144765734672546, "regret": 0.004242465831339359, "entropy": 0.20006051659584045, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
63
+ {"ts": "2026-02-20T15:11:54.381269Z", "loop": 46, "env_steps": 28876799, "loss": 0.05125051736831665, "avg_return": 0.9141619205474854, "regret": 0.004482488613575697, "entropy": 0.2037288248538971, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
64
+ {"ts": "2026-02-20T15:11:55.307945Z", "loop": 47, "env_steps": 29491199, "loss": 0.0531039722263813, "avg_return": 0.9130945205688477, "regret": 0.004782821051776409, "entropy": 0.20707325637340546, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
65
+ {"ts": "2026-02-20T15:11:56.231091Z", "loop": 48, "env_steps": 30105599, "loss": 0.05419379472732544, "avg_return": 0.9131142497062683, "regret": 0.00511831184849143, "entropy": 0.2026086002588272, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
66
+ {"ts": "2026-02-20T15:11:57.156082Z", "loop": 49, "env_steps": 30719999, "loss": 0.049908243119716644, "avg_return": 0.9131175875663757, "regret": 0.005725029855966568, "entropy": 0.19391946494579315, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
67
+ {"ts": "2026-02-20T15:11:58.082806Z", "loop": 50, "env_steps": 31334399, "loss": 0.04839767515659332, "avg_return": 0.9124342799186707, "regret": 0.005636340007185936, "entropy": 0.1874157190322876, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
68
+ {"ts": "2026-02-20T15:11:59.007175Z", "loop": 51, "env_steps": 31948799, "loss": 0.047373153269290924, "avg_return": 0.9123470187187195, "regret": 0.005460516083985567, "entropy": 0.18418215215206146, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
69
+ {"ts": "2026-02-20T15:11:59.933916Z", "loop": 52, "env_steps": 32563199, "loss": 0.04660026356577873, "avg_return": 0.912553608417511, "regret": 0.005135168321430683, "entropy": 0.17801114916801453, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
70
+ {"ts": "2026-02-20T15:12:00.860943Z", "loop": 53, "env_steps": 33177599, "loss": 0.0468909814953804, "avg_return": 0.9133585691452026, "regret": 0.004764324054121971, "entropy": 0.17777855694293976, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
71
+ {"ts": "2026-02-20T15:12:01.789070Z", "loop": 54, "env_steps": 33791999, "loss": 0.04701732471585274, "avg_return": 0.913378119468689, "regret": 0.004561996553093195, "entropy": 0.1745351254940033, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
72
+ {"ts": "2026-02-20T15:12:02.717179Z", "loop": 55, "env_steps": 34406399, "loss": 0.045685939490795135, "avg_return": 0.9132937788963318, "regret": 0.004603891633450985, "entropy": 0.179330512881279, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
73
+ {"ts": "2026-02-20T15:12:03.644865Z", "loop": 56, "env_steps": 35020799, "loss": 0.045520711690187454, "avg_return": 0.9138346314430237, "regret": 0.004835526924580336, "entropy": 0.17907670140266418, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
74
+ {"ts": "2026-02-20T15:12:04.572323Z", "loop": 57, "env_steps": 35635199, "loss": 0.0462702177464962, "avg_return": 0.9132933616638184, "regret": 0.00489508593454957, "entropy": 0.17841112613677979, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
75
+ {"ts": "2026-02-20T15:12:05.502437Z", "loop": 58, "env_steps": 36249599, "loss": 0.04481881856918335, "avg_return": 0.9146080017089844, "regret": 0.004870634991675615, "entropy": 0.17550428211688995, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
76
+ {"ts": "2026-02-20T15:12:06.432276Z", "loop": 59, "env_steps": 36863999, "loss": 0.04665354639291763, "avg_return": 0.914064884185791, "regret": 0.004656847566366196, "entropy": 0.18158631026744843, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
77
+ {"ts": "2026-02-20T15:12:07.362739Z", "loop": 60, "env_steps": 37478399, "loss": 0.049357157200574875, "avg_return": 0.9140632152557373, "regret": 0.004528329707682133, "entropy": 0.19274312257766724, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
78
+ {"ts": "2026-02-20T15:12:08.296338Z", "loop": 61, "env_steps": 38092799, "loss": 0.05239371210336685, "avg_return": 0.913978099822998, "regret": 0.004446536302566528, "entropy": 0.20644554495811462, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
79
+ {"ts": "2026-02-20T15:12:09.226059Z", "loop": 62, "env_steps": 38707199, "loss": 0.05332847312092781, "avg_return": 0.9130237102508545, "regret": 0.004401105456054211, "entropy": 0.20517081022262573, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
80
+ {"ts": "2026-02-20T15:12:10.156280Z", "loop": 63, "env_steps": 39321599, "loss": 0.05241856351494789, "avg_return": 0.9144586324691772, "regret": 0.004337889142334461, "entropy": 0.20803605020046234, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
81
+ {"ts": "2026-02-20T15:12:11.086219Z", "loop": 64, "env_steps": 39935999, "loss": 0.05415841564536095, "avg_return": 0.9142010807991028, "regret": 0.00425015389919281, "entropy": 0.212845116853714, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
82
+ {"ts": "2026-02-20T15:12:12.014317Z", "loop": 65, "env_steps": 40550399, "loss": 0.05330940708518028, "avg_return": 0.9142569303512573, "regret": 0.004199168179184198, "entropy": 0.20781055092811584, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
83
+ {"ts": "2026-02-20T15:12:12.948136Z", "loop": 66, "env_steps": 41164799, "loss": 0.052729539573192596, "avg_return": 0.914432168006897, "regret": 0.0042247953824698925, "entropy": 0.2045881599187851, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
84
+ {"ts": "2026-02-20T15:12:13.876843Z", "loop": 67, "env_steps": 41779199, "loss": 0.05321582034230232, "avg_return": 0.914793848991394, "regret": 0.004341484047472477, "entropy": 0.2016538679599762, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
85
+ {"ts": "2026-02-20T15:12:14.806131Z", "loop": 68, "env_steps": 42393599, "loss": 0.04985136166214943, "avg_return": 0.9136470556259155, "regret": 0.004539605230093002, "entropy": 0.1915643960237503, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
86
+ {"ts": "2026-02-20T15:12:15.735264Z", "loop": 69, "env_steps": 43007999, "loss": 0.04936384782195091, "avg_return": 0.9131110906600952, "regret": 0.004753380082547665, "entropy": 0.19480878114700317, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
87
+ {"ts": "2026-02-20T15:12:16.662876Z", "loop": 70, "env_steps": 43622399, "loss": 0.046939462423324585, "avg_return": 0.9133452773094177, "regret": 0.004717383999377489, "entropy": 0.18131321668624878, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
88
+ {"ts": "2026-02-20T15:12:17.590323Z", "loop": 71, "env_steps": 44236799, "loss": 0.050143614411354065, "avg_return": 0.9142476916313171, "regret": 0.004581494256854057, "entropy": 0.19756759703159332, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
89
+ {"ts": "2026-02-20T15:12:18.519442Z", "loop": 72, "env_steps": 44851199, "loss": 0.05008978769183159, "avg_return": 0.9133825898170471, "regret": 0.004552681464701891, "entropy": 0.19370140135288239, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
90
+ {"ts": "2026-02-20T15:12:19.448517Z", "loop": 73, "env_steps": 45465599, "loss": 0.0509028285741806, "avg_return": 0.9137506484985352, "regret": 0.004467798396945, "entropy": 0.19510915875434875, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
91
+ {"ts": "2026-02-20T15:12:20.374411Z", "loop": 74, "env_steps": 46079999, "loss": 0.050648126751184464, "avg_return": 0.9140257835388184, "regret": 0.004320131614804268, "entropy": 0.1942904144525528, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
92
+ {"ts": "2026-02-20T15:12:21.303536Z", "loop": 75, "env_steps": 46694399, "loss": 0.05400993674993515, "avg_return": 0.914624035358429, "regret": 0.00412228237837553, "entropy": 0.20562681555747986, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
93
+ {"ts": "2026-02-20T15:12:22.229811Z", "loop": 76, "env_steps": 47308799, "loss": 0.0534718781709671, "avg_return": 0.9150938391685486, "regret": 0.004002721514552832, "entropy": 0.20516468584537506, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
94
+ {"ts": "2026-02-20T15:12:23.156807Z", "loop": 77, "env_steps": 47923199, "loss": 0.052657801657915115, "avg_return": 0.9146759510040283, "regret": 0.003937916364520788, "entropy": 0.20420651137828827, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
95
+ {"ts": "2026-02-20T15:12:24.086553Z", "loop": 78, "env_steps": 48537599, "loss": 0.050804801285266876, "avg_return": 0.9147161841392517, "regret": 0.003911955747753382, "entropy": 0.1979532688856125, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
96
+ {"ts": "2026-02-20T15:12:25.014994Z", "loop": 79, "env_steps": 49151999, "loss": 0.04604850709438324, "avg_return": 0.9146710634231567, "regret": 0.003972034435719252, "entropy": 0.18039748072624207, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
97
+ {"ts": "2026-02-20T15:12:25.943355Z", "loop": 80, "env_steps": 49766399, "loss": 0.04076342284679413, "avg_return": 0.9136733412742615, "regret": 0.004086306784301996, "entropy": 0.15896055102348328, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
98
+ {"ts": "2026-02-20T15:37:36.468767Z", "loop": 0, "env_steps": 614399, "loss": 0.038459062576293945, "avg_return": 0.9144043326377869, "regret": 0.004308843053877354, "entropy": 0.14913484454154968, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
99
+ {"ts": "2026-02-20T15:37:37.402566Z", "loop": 1, "env_steps": 1228799, "loss": 0.04305032268166542, "avg_return": 0.914141058921814, "regret": 0.005145789589732885, "entropy": 0.16546086966991425, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
100
+ {"ts": "2026-02-20T15:37:38.329955Z", "loop": 2, "env_steps": 1843199, "loss": 0.042838335037231445, "avg_return": 0.9133297801017761, "regret": 0.004989685025066137, "entropy": 0.16842970252037048, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
101
+ {"ts": "2026-02-20T15:37:39.259650Z", "loop": 3, "env_steps": 2457599, "loss": 0.049289848655462265, "avg_return": 0.9130585193634033, "regret": 0.005611793138086796, "entropy": 0.18803898990154266, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
102
+ {"ts": "2026-02-20T15:37:40.181461Z", "loop": 4, "env_steps": 3071999, "loss": 0.05503948777914047, "avg_return": 0.9109735488891602, "regret": 0.007410373538732529, "entropy": 0.21352212131023407, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
103
+ {"ts": "2026-02-20T15:37:41.108236Z", "loop": 5, "env_steps": 3686399, "loss": 0.05555526912212372, "avg_return": 0.9085718989372253, "regret": 0.009732013568282127, "entropy": 0.22367124259471893, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
104
+ {"ts": "2026-02-20T15:37:42.035772Z", "loop": 6, "env_steps": 4300799, "loss": 0.05597533658146858, "avg_return": 0.9098407030105591, "regret": 0.0080783162266016, "entropy": 0.2134706676006317, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
105
+ {"ts": "2026-02-20T15:37:42.962679Z", "loop": 7, "env_steps": 4915199, "loss": 0.05279890075325966, "avg_return": 0.912228524684906, "regret": 0.006940040271729231, "entropy": 0.20506125688552856, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
106
+ {"ts": "2026-02-20T15:37:43.890634Z", "loop": 8, "env_steps": 5529599, "loss": 0.05076589435338974, "avg_return": 0.9128298163414001, "regret": 0.005884145386517048, "entropy": 0.19164735078811646, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
107
+ {"ts": "2026-02-20T15:37:44.819100Z", "loop": 9, "env_steps": 6143999, "loss": 0.04389328137040138, "avg_return": 0.9135256409645081, "regret": 0.004890759941190481, "entropy": 0.16351893544197083, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
108
+ {"ts": "2026-02-20T15:37:45.744146Z", "loop": 10, "env_steps": 6758399, "loss": 0.03995446115732193, "avg_return": 0.9134226441383362, "regret": 0.0043883416801691055, "entropy": 0.15135043859481812, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
109
+ {"ts": "2026-02-20T15:37:46.665451Z", "loop": 11, "env_steps": 7372799, "loss": 0.03796378895640373, "avg_return": 0.9143897891044617, "regret": 0.004246285185217857, "entropy": 0.14120905101299286, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
110
+ {"ts": "2026-02-20T15:37:47.590327Z", "loop": 12, "env_steps": 7987199, "loss": 0.03703838586807251, "avg_return": 0.9139742255210876, "regret": 0.0041516912169754505, "entropy": 0.14204582571983337, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
111
+ {"ts": "2026-02-20T15:37:48.514048Z", "loop": 13, "env_steps": 8601599, "loss": 0.036254607141017914, "avg_return": 0.9146824479103088, "regret": 0.004124278202652931, "entropy": 0.14249636232852936, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
112
+ {"ts": "2026-02-20T15:37:49.441005Z", "loop": 14, "env_steps": 9215999, "loss": 0.03912505879998207, "avg_return": 0.9140971899032593, "regret": 0.004205651581287384, "entropy": 0.15343046188354492, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
113
+ {"ts": "2026-02-20T15:37:50.368786Z", "loop": 15, "env_steps": 9830399, "loss": 0.043059494346380234, "avg_return": 0.9140105247497559, "regret": 0.004545097704976797, "entropy": 0.16417203843593597, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
114
+ {"ts": "2026-02-20T15:37:51.296942Z", "loop": 16, "env_steps": 10444799, "loss": 0.04881095141172409, "avg_return": 0.9127726554870605, "regret": 0.005157078616321087, "entropy": 0.1844228208065033, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
115
+ {"ts": "2026-02-20T15:37:52.224480Z", "loop": 17, "env_steps": 11059199, "loss": 0.05005049332976341, "avg_return": 0.9135828018188477, "regret": 0.005261595826596022, "entropy": 0.19199229776859283, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
116
+ {"ts": "2026-02-20T15:37:53.153072Z", "loop": 18, "env_steps": 11673599, "loss": 0.04876140505075455, "avg_return": 0.9132229089736938, "regret": 0.00511329947039485, "entropy": 0.19011464715003967, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
117
+ {"ts": "2026-02-20T15:37:54.082215Z", "loop": 19, "env_steps": 12287999, "loss": 0.04967671260237694, "avg_return": 0.9128940105438232, "regret": 0.0049299877136945724, "entropy": 0.19220764935016632, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
118
+ {"ts": "2026-02-20T15:37:55.011991Z", "loop": 20, "env_steps": 12902399, "loss": 0.05157233402132988, "avg_return": 0.9136543869972229, "regret": 0.004945225082337856, "entropy": 0.20100222527980804, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
119
+ {"ts": "2026-02-20T15:37:55.940529Z", "loop": 21, "env_steps": 13516799, "loss": 0.053730230778455734, "avg_return": 0.9133966565132141, "regret": 0.004896321799606085, "entropy": 0.2068491131067276, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
120
+ {"ts": "2026-02-20T15:37:56.866325Z", "loop": 22, "env_steps": 14131199, "loss": 0.05553211271762848, "avg_return": 0.913227379322052, "regret": 0.00482122041285038, "entropy": 0.2085137963294983, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
121
+ {"ts": "2026-02-20T15:37:57.800722Z", "loop": 23, "env_steps": 14745599, "loss": 0.05334676429629326, "avg_return": 0.9138824939727783, "regret": 0.00471537746489048, "entropy": 0.20375385880470276, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
122
+ {"ts": "2026-02-20T15:37:58.731652Z", "loop": 24, "env_steps": 15359999, "loss": 0.054690152406692505, "avg_return": 0.9141449332237244, "regret": 0.004711857531219721, "entropy": 0.20919829607009888, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
123
+ {"ts": "2026-02-20T15:37:59.662698Z", "loop": 25, "env_steps": 15974399, "loss": 0.05489712953567505, "avg_return": 0.9134702682495117, "regret": 0.004917492624372244, "entropy": 0.2113226354122162, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
124
+ {"ts": "2026-02-20T15:38:00.594156Z", "loop": 26, "env_steps": 16588799, "loss": 0.05722189322113991, "avg_return": 0.9130019545555115, "regret": 0.005538491532206535, "entropy": 0.22079502046108246, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
125
+ {"ts": "2026-02-20T15:38:01.525645Z", "loop": 27, "env_steps": 17203199, "loss": 0.05423341691493988, "avg_return": 0.9133304953575134, "regret": 0.005992687772959471, "entropy": 0.21447180211544037, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
126
+ {"ts": "2026-02-20T15:38:02.458795Z", "loop": 28, "env_steps": 17817599, "loss": 0.05511590093374252, "avg_return": 0.9116150140762329, "regret": 0.006190338637679815, "entropy": 0.21591898798942566, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
127
+ {"ts": "2026-02-20T15:38:03.385399Z", "loop": 29, "env_steps": 18431999, "loss": 0.05198509991168976, "avg_return": 0.9118152260780334, "regret": 0.006502676755189896, "entropy": 0.20928069949150085, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
128
+ {"ts": "2026-02-20T15:38:04.310324Z", "loop": 30, "env_steps": 19046399, "loss": 0.052754003554582596, "avg_return": 0.9122692346572876, "regret": 0.006323689594864845, "entropy": 0.20549479126930237, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
129
+ {"ts": "2026-02-20T15:38:05.238355Z", "loop": 31, "env_steps": 19660799, "loss": 0.052055466920137405, "avg_return": 0.9124749898910522, "regret": 0.00627649761736393, "entropy": 0.19896496832370758, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
130
+ {"ts": "2026-02-20T15:38:06.167275Z", "loop": 32, "env_steps": 20275199, "loss": 0.0507308766245842, "avg_return": 0.9116406440734863, "regret": 0.006176636554300785, "entropy": 0.2011982500553131, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
131
+ {"ts": "2026-02-20T15:38:07.098818Z", "loop": 33, "env_steps": 20889599, "loss": 0.05132613331079483, "avg_return": 0.9138214588165283, "regret": 0.0057111987844109535, "entropy": 0.19886808097362518, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
132
+ {"ts": "2026-02-20T15:38:08.029045Z", "loop": 34, "env_steps": 21503999, "loss": 0.05241093039512634, "avg_return": 0.9129173159599304, "regret": 0.005308059975504875, "entropy": 0.2036304920911789, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
133
+ {"ts": "2026-02-20T15:38:08.955647Z", "loop": 35, "env_steps": 22118399, "loss": 0.052897609770298004, "avg_return": 0.9141751527786255, "regret": 0.004898912739008665, "entropy": 0.20442193746566772, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
134
+ {"ts": "2026-02-20T15:38:09.882348Z", "loop": 36, "env_steps": 22732799, "loss": 0.05398102104663849, "avg_return": 0.913618266582489, "regret": 0.004650804214179516, "entropy": 0.21441315114498138, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
135
+ {"ts": "2026-02-20T15:38:10.810467Z", "loop": 37, "env_steps": 23347199, "loss": 0.052688565105199814, "avg_return": 0.9147119522094727, "regret": 0.004488404840230942, "entropy": 0.20510266721248627, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
136
+ {"ts": "2026-02-20T15:38:11.759275Z", "loop": 38, "env_steps": 23961599, "loss": 0.04847056418657303, "avg_return": 0.9138769507408142, "regret": 0.004431146662682295, "entropy": 0.1905696839094162, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
137
+ {"ts": "2026-02-20T15:38:13.401019Z", "loop": 39, "env_steps": 24575999, "loss": 0.047192227095365524, "avg_return": 0.9146565198898315, "regret": 0.0044012898579239845, "entropy": 0.182176873087883, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
138
+ {"ts": "2026-02-20T15:38:14.501205Z", "loop": 40, "env_steps": 25190399, "loss": 0.046322982758283615, "avg_return": 0.9141542911529541, "regret": 0.004372016526758671, "entropy": 0.18115457892417908, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
139
+ {"ts": "2026-02-20T15:38:15.825281Z", "loop": 41, "env_steps": 25804799, "loss": 0.04591471701860428, "avg_return": 0.914177656173706, "regret": 0.004312243312597275, "entropy": 0.17777203023433685, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
140
+ {"ts": "2026-02-20T15:38:17.891061Z", "loop": 42, "env_steps": 26419199, "loss": 0.04703698679804802, "avg_return": 0.9138143062591553, "regret": 0.004224626813083887, "entropy": 0.1886642575263977, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
141
+ {"ts": "2026-02-20T15:38:19.047042Z", "loop": 43, "env_steps": 27033599, "loss": 0.050354450941085815, "avg_return": 0.9139518737792969, "regret": 0.004152423236519098, "entropy": 0.1983119547367096, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
142
+ {"ts": "2026-02-20T15:38:20.503885Z", "loop": 44, "env_steps": 27647999, "loss": 0.050561774522066116, "avg_return": 0.9143680930137634, "regret": 0.004134788177907467, "entropy": 0.1951211839914322, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
143
+ {"ts": "2026-02-20T15:38:22.291765Z", "loop": 45, "env_steps": 28262399, "loss": 0.05251600593328476, "avg_return": 0.9144765734672546, "regret": 0.004242465831339359, "entropy": 0.20006051659584045, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
144
+ {"ts": "2026-02-20T15:38:23.703146Z", "loop": 46, "env_steps": 28876799, "loss": 0.05125051736831665, "avg_return": 0.9141619205474854, "regret": 0.004482488613575697, "entropy": 0.2037288248538971, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
145
+ {"ts": "2026-02-20T15:38:25.116988Z", "loop": 47, "env_steps": 29491199, "loss": 0.0531039722263813, "avg_return": 0.9130945205688477, "regret": 0.004782821051776409, "entropy": 0.20707325637340546, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
146
+ {"ts": "2026-02-20T15:38:26.048200Z", "loop": 48, "env_steps": 30105599, "loss": 0.05419379472732544, "avg_return": 0.9131142497062683, "regret": 0.00511831184849143, "entropy": 0.2026086002588272, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
147
+ {"ts": "2026-02-20T15:38:26.975435Z", "loop": 49, "env_steps": 30719999, "loss": 0.049908243119716644, "avg_return": 0.9131175875663757, "regret": 0.005725029855966568, "entropy": 0.19391946494579315, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
148
+ {"ts": "2026-02-20T15:38:27.903436Z", "loop": 50, "env_steps": 31334399, "loss": 0.04839767515659332, "avg_return": 0.9124342799186707, "regret": 0.005636340007185936, "entropy": 0.1874157190322876, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
149
+ {"ts": "2026-02-20T15:38:28.830278Z", "loop": 51, "env_steps": 31948799, "loss": 0.047373153269290924, "avg_return": 0.9123470187187195, "regret": 0.005460516083985567, "entropy": 0.18418215215206146, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
150
+ {"ts": "2026-02-20T15:38:29.759793Z", "loop": 52, "env_steps": 32563199, "loss": 0.04660026356577873, "avg_return": 0.912553608417511, "regret": 0.005135168321430683, "entropy": 0.17801114916801453, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
151
+ {"ts": "2026-02-20T15:38:30.689577Z", "loop": 53, "env_steps": 33177599, "loss": 0.0468909814953804, "avg_return": 0.9133585691452026, "regret": 0.004764324054121971, "entropy": 0.17777855694293976, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
152
+ {"ts": "2026-02-20T15:38:31.619723Z", "loop": 54, "env_steps": 33791999, "loss": 0.04701732471585274, "avg_return": 0.913378119468689, "regret": 0.004561996553093195, "entropy": 0.1745351254940033, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
153
+ {"ts": "2026-02-20T15:38:32.549770Z", "loop": 55, "env_steps": 34406399, "loss": 0.045685939490795135, "avg_return": 0.9132937788963318, "regret": 0.004603891633450985, "entropy": 0.179330512881279, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
154
+ {"ts": "2026-02-20T15:38:33.480048Z", "loop": 56, "env_steps": 35020799, "loss": 0.045520711690187454, "avg_return": 0.9138346314430237, "regret": 0.004835526924580336, "entropy": 0.17907670140266418, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
155
+ {"ts": "2026-02-20T15:38:34.409414Z", "loop": 57, "env_steps": 35635199, "loss": 0.0462702177464962, "avg_return": 0.9132933616638184, "regret": 0.00489508593454957, "entropy": 0.17841112613677979, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
156
+ {"ts": "2026-02-20T15:38:35.338892Z", "loop": 58, "env_steps": 36249599, "loss": 0.04481881856918335, "avg_return": 0.9146080017089844, "regret": 0.004870634991675615, "entropy": 0.17550428211688995, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
157
+ {"ts": "2026-02-20T15:38:36.266201Z", "loop": 59, "env_steps": 36863999, "loss": 0.04665354639291763, "avg_return": 0.914064884185791, "regret": 0.004656847566366196, "entropy": 0.18158631026744843, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
158
+ {"ts": "2026-02-20T15:38:37.190706Z", "loop": 60, "env_steps": 37478399, "loss": 0.049357157200574875, "avg_return": 0.9140632152557373, "regret": 0.004528329707682133, "entropy": 0.19274312257766724, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
159
+ {"ts": "2026-02-20T15:38:38.116569Z", "loop": 61, "env_steps": 38092799, "loss": 0.05239371210336685, "avg_return": 0.913978099822998, "regret": 0.004446536302566528, "entropy": 0.20644554495811462, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
160
+ {"ts": "2026-02-20T15:38:39.040296Z", "loop": 62, "env_steps": 38707199, "loss": 0.05332847312092781, "avg_return": 0.9130237102508545, "regret": 0.004401105456054211, "entropy": 0.20517081022262573, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
161
+ {"ts": "2026-02-20T15:38:39.967025Z", "loop": 63, "env_steps": 39321599, "loss": 0.05241856351494789, "avg_return": 0.9144586324691772, "regret": 0.004337889142334461, "entropy": 0.20803605020046234, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
162
+ {"ts": "2026-02-20T15:38:40.894456Z", "loop": 64, "env_steps": 39935999, "loss": 0.05415841564536095, "avg_return": 0.9142010807991028, "regret": 0.00425015389919281, "entropy": 0.212845116853714, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
163
+ {"ts": "2026-02-20T15:38:41.820519Z", "loop": 65, "env_steps": 40550399, "loss": 0.05330940708518028, "avg_return": 0.9142569303512573, "regret": 0.004199168179184198, "entropy": 0.20781055092811584, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
164
+ {"ts": "2026-02-20T15:38:42.745800Z", "loop": 66, "env_steps": 41164799, "loss": 0.052729539573192596, "avg_return": 0.914432168006897, "regret": 0.0042247953824698925, "entropy": 0.2045881599187851, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
165
+ {"ts": "2026-02-20T15:38:43.674080Z", "loop": 67, "env_steps": 41779199, "loss": 0.05321582034230232, "avg_return": 0.914793848991394, "regret": 0.004341484047472477, "entropy": 0.2016538679599762, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
166
+ {"ts": "2026-02-20T15:38:44.602058Z", "loop": 68, "env_steps": 42393599, "loss": 0.04985136166214943, "avg_return": 0.9136470556259155, "regret": 0.004539605230093002, "entropy": 0.1915643960237503, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
167
+ {"ts": "2026-02-20T15:38:45.529723Z", "loop": 69, "env_steps": 43007999, "loss": 0.04936384782195091, "avg_return": 0.9131110906600952, "regret": 0.004753380082547665, "entropy": 0.19480878114700317, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
168
+ {"ts": "2026-02-20T15:38:46.458187Z", "loop": 70, "env_steps": 43622399, "loss": 0.046939462423324585, "avg_return": 0.9133452773094177, "regret": 0.004717383999377489, "entropy": 0.18131321668624878, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
169
+ {"ts": "2026-02-20T15:38:47.384430Z", "loop": 71, "env_steps": 44236799, "loss": 0.050143614411354065, "avg_return": 0.9142476916313171, "regret": 0.004581494256854057, "entropy": 0.19756759703159332, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
170
+ {"ts": "2026-02-20T15:38:48.313123Z", "loop": 72, "env_steps": 44851199, "loss": 0.05008978769183159, "avg_return": 0.9133825898170471, "regret": 0.004552681464701891, "entropy": 0.19370140135288239, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
171
+ {"ts": "2026-02-20T15:38:49.241927Z", "loop": 73, "env_steps": 45465599, "loss": 0.0509028285741806, "avg_return": 0.9137506484985352, "regret": 0.004467798396945, "entropy": 0.19510915875434875, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
172
+ {"ts": "2026-02-20T15:38:50.169800Z", "loop": 74, "env_steps": 46079999, "loss": 0.050648126751184464, "avg_return": 0.9140257835388184, "regret": 0.004320131614804268, "entropy": 0.1942904144525528, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
173
+ {"ts": "2026-02-20T15:38:51.097485Z", "loop": 75, "env_steps": 46694399, "loss": 0.05400993674993515, "avg_return": 0.914624035358429, "regret": 0.00412228237837553, "entropy": 0.20562681555747986, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
174
+ {"ts": "2026-02-20T15:38:52.025310Z", "loop": 76, "env_steps": 47308799, "loss": 0.0534718781709671, "avg_return": 0.9150938391685486, "regret": 0.004002721514552832, "entropy": 0.20516468584537506, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
175
+ {"ts": "2026-02-20T15:38:52.960718Z", "loop": 77, "env_steps": 47923199, "loss": 0.052657801657915115, "avg_return": 0.9146759510040283, "regret": 0.003937916364520788, "entropy": 0.20420651137828827, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
176
+ {"ts": "2026-02-20T15:38:53.888560Z", "loop": 78, "env_steps": 48537599, "loss": 0.050804801285266876, "avg_return": 0.9147161841392517, "regret": 0.003911955747753382, "entropy": 0.1979532688856125, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
177
+ {"ts": "2026-02-20T15:38:54.820649Z", "loop": 79, "env_steps": 49151999, "loss": 0.04604850709438324, "avg_return": 0.9146710634231567, "regret": 0.003972034435719252, "entropy": 0.18039748072624207, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
178
+ {"ts": "2026-02-20T15:38:55.751047Z", "loop": 80, "env_steps": 49766399, "loss": 0.04076342284679413, "avg_return": 0.9136733412742615, "regret": 0.004086306784301996, "entropy": 0.15896055102348328, "lr": 5e-05, "discount_rate": 0.99, "num_rollout_steps": 64}
al_0.6_g_0.98_id_17_seed_980617/patt_diff_h_-8e-01_ld-opt_0/train.log ADDED
@@ -0,0 +1,178 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [2026-02-20T15:08:15.003567Z] Loop 0: Loss: 3.85e-02, Avg Return: 0.914, Regret: 0.0043, Entropy: 0.1491
2
+ [2026-02-20T15:08:15.930902Z] Loop 1: Loss: 4.31e-02, Avg Return: 0.914, Regret: 0.0051, Entropy: 0.1655
3
+ [2026-02-20T15:08:16.856492Z] Loop 2: Loss: 4.28e-02, Avg Return: 0.913, Regret: 0.0050, Entropy: 0.1684
4
+ [2026-02-20T15:08:17.780882Z] Loop 3: Loss: 4.93e-02, Avg Return: 0.913, Regret: 0.0056, Entropy: 0.1880
5
+ [2026-02-20T15:08:18.705383Z] Loop 4: Loss: 5.50e-02, Avg Return: 0.911, Regret: 0.0074, Entropy: 0.2135
6
+ [2026-02-20T15:08:19.629502Z] Loop 5: Loss: 5.56e-02, Avg Return: 0.909, Regret: 0.0097, Entropy: 0.2237
7
+ [2026-02-20T15:08:20.552817Z] Loop 6: Loss: 5.60e-02, Avg Return: 0.910, Regret: 0.0081, Entropy: 0.2135
8
+ [2026-02-20T15:08:21.476661Z] Loop 7: Loss: 5.28e-02, Avg Return: 0.912, Regret: 0.0069, Entropy: 0.2051
9
+ [2026-02-20T15:08:22.402193Z] Loop 8: Loss: 5.08e-02, Avg Return: 0.913, Regret: 0.0059, Entropy: 0.1916
10
+ [2026-02-20T15:08:23.330566Z] Loop 9: Loss: 4.39e-02, Avg Return: 0.914, Regret: 0.0049, Entropy: 0.1635
11
+ [2026-02-20T15:08:24.252544Z] Loop 10: Loss: 4.00e-02, Avg Return: 0.913, Regret: 0.0044, Entropy: 0.1514
12
+ [2026-02-20T15:08:25.175373Z] Loop 11: Loss: 3.80e-02, Avg Return: 0.914, Regret: 0.0042, Entropy: 0.1412
13
+ [2026-02-20T15:08:26.099761Z] Loop 12: Loss: 3.70e-02, Avg Return: 0.914, Regret: 0.0042, Entropy: 0.1420
14
+ [2026-02-20T15:08:27.021354Z] Loop 13: Loss: 3.63e-02, Avg Return: 0.915, Regret: 0.0041, Entropy: 0.1425
15
+ [2026-02-20T15:08:27.945053Z] Loop 14: Loss: 3.91e-02, Avg Return: 0.914, Regret: 0.0042, Entropy: 0.1534
16
+ [2026-02-20T15:08:28.868489Z] Loop 15: Loss: 4.31e-02, Avg Return: 0.914, Regret: 0.0045, Entropy: 0.1642
17
+ [2026-02-20T15:11:11.616100Z] Loop 0: Loss: 3.85e-02, Avg Return: 0.914, Regret: 0.0043, Entropy: 0.1491
18
+ [2026-02-20T15:11:12.548846Z] Loop 1: Loss: 4.31e-02, Avg Return: 0.914, Regret: 0.0051, Entropy: 0.1655
19
+ [2026-02-20T15:11:13.476173Z] Loop 2: Loss: 4.28e-02, Avg Return: 0.913, Regret: 0.0050, Entropy: 0.1684
20
+ [2026-02-20T15:11:14.404892Z] Loop 3: Loss: 4.93e-02, Avg Return: 0.913, Regret: 0.0056, Entropy: 0.1880
21
+ [2026-02-20T15:11:15.333240Z] Loop 4: Loss: 5.50e-02, Avg Return: 0.911, Regret: 0.0074, Entropy: 0.2135
22
+ [2026-02-20T15:11:16.268221Z] Loop 5: Loss: 5.56e-02, Avg Return: 0.909, Regret: 0.0097, Entropy: 0.2237
23
+ [2026-02-20T15:11:17.196926Z] Loop 6: Loss: 5.60e-02, Avg Return: 0.910, Regret: 0.0081, Entropy: 0.2135
24
+ [2026-02-20T15:11:18.125915Z] Loop 7: Loss: 5.28e-02, Avg Return: 0.912, Regret: 0.0069, Entropy: 0.2051
25
+ [2026-02-20T15:11:19.051290Z] Loop 8: Loss: 5.08e-02, Avg Return: 0.913, Regret: 0.0059, Entropy: 0.1916
26
+ [2026-02-20T15:11:19.974981Z] Loop 9: Loss: 4.39e-02, Avg Return: 0.914, Regret: 0.0049, Entropy: 0.1635
27
+ [2026-02-20T15:11:20.913035Z] Loop 10: Loss: 4.00e-02, Avg Return: 0.913, Regret: 0.0044, Entropy: 0.1514
28
+ [2026-02-20T15:11:21.838468Z] Loop 11: Loss: 3.80e-02, Avg Return: 0.914, Regret: 0.0042, Entropy: 0.1412
29
+ [2026-02-20T15:11:22.761794Z] Loop 12: Loss: 3.70e-02, Avg Return: 0.914, Regret: 0.0042, Entropy: 0.1420
30
+ [2026-02-20T15:11:23.686710Z] Loop 13: Loss: 3.63e-02, Avg Return: 0.915, Regret: 0.0041, Entropy: 0.1425
31
+ [2026-02-20T15:11:24.611920Z] Loop 14: Loss: 3.91e-02, Avg Return: 0.914, Regret: 0.0042, Entropy: 0.1534
32
+ [2026-02-20T15:11:25.537865Z] Loop 15: Loss: 4.31e-02, Avg Return: 0.914, Regret: 0.0045, Entropy: 0.1642
33
+ [2026-02-20T15:11:26.540290Z] Loop 16: Loss: 4.88e-02, Avg Return: 0.913, Regret: 0.0052, Entropy: 0.1844
34
+ [2026-02-20T15:11:27.478388Z] Loop 17: Loss: 5.01e-02, Avg Return: 0.914, Regret: 0.0053, Entropy: 0.1920
35
+ [2026-02-20T15:11:28.418594Z] Loop 18: Loss: 4.88e-02, Avg Return: 0.913, Regret: 0.0051, Entropy: 0.1901
36
+ [2026-02-20T15:11:29.346420Z] Loop 19: Loss: 4.97e-02, Avg Return: 0.913, Regret: 0.0049, Entropy: 0.1922
37
+ [2026-02-20T15:11:30.283499Z] Loop 20: Loss: 5.16e-02, Avg Return: 0.914, Regret: 0.0049, Entropy: 0.2010
38
+ [2026-02-20T15:11:31.208809Z] Loop 21: Loss: 5.37e-02, Avg Return: 0.913, Regret: 0.0049, Entropy: 0.2068
39
+ [2026-02-20T15:11:32.133771Z] Loop 22: Loss: 5.55e-02, Avg Return: 0.913, Regret: 0.0048, Entropy: 0.2085
40
+ [2026-02-20T15:11:33.057041Z] Loop 23: Loss: 5.33e-02, Avg Return: 0.914, Regret: 0.0047, Entropy: 0.2038
41
+ [2026-02-20T15:11:33.986575Z] Loop 24: Loss: 5.47e-02, Avg Return: 0.914, Regret: 0.0047, Entropy: 0.2092
42
+ [2026-02-20T15:11:34.922765Z] Loop 25: Loss: 5.49e-02, Avg Return: 0.913, Regret: 0.0049, Entropy: 0.2113
43
+ [2026-02-20T15:11:35.849311Z] Loop 26: Loss: 5.72e-02, Avg Return: 0.913, Regret: 0.0055, Entropy: 0.2208
44
+ [2026-02-20T15:11:36.774709Z] Loop 27: Loss: 5.42e-02, Avg Return: 0.913, Regret: 0.0060, Entropy: 0.2145
45
+ [2026-02-20T15:11:37.699830Z] Loop 28: Loss: 5.51e-02, Avg Return: 0.912, Regret: 0.0062, Entropy: 0.2159
46
+ [2026-02-20T15:11:38.625770Z] Loop 29: Loss: 5.20e-02, Avg Return: 0.912, Regret: 0.0065, Entropy: 0.2093
47
+ [2026-02-20T15:11:39.551905Z] Loop 30: Loss: 5.28e-02, Avg Return: 0.912, Regret: 0.0063, Entropy: 0.2055
48
+ [2026-02-20T15:11:40.479334Z] Loop 31: Loss: 5.21e-02, Avg Return: 0.912, Regret: 0.0063, Entropy: 0.1990
49
+ [2026-02-20T15:11:41.404408Z] Loop 32: Loss: 5.07e-02, Avg Return: 0.912, Regret: 0.0062, Entropy: 0.2012
50
+ [2026-02-20T15:11:42.331136Z] Loop 33: Loss: 5.13e-02, Avg Return: 0.914, Regret: 0.0057, Entropy: 0.1989
51
+ [2026-02-20T15:11:43.256830Z] Loop 34: Loss: 5.24e-02, Avg Return: 0.913, Regret: 0.0053, Entropy: 0.2036
52
+ [2026-02-20T15:11:44.182862Z] Loop 35: Loss: 5.29e-02, Avg Return: 0.914, Regret: 0.0049, Entropy: 0.2044
53
+ [2026-02-20T15:11:45.110327Z] Loop 36: Loss: 5.40e-02, Avg Return: 0.914, Regret: 0.0047, Entropy: 0.2144
54
+ [2026-02-20T15:11:46.036171Z] Loop 37: Loss: 5.27e-02, Avg Return: 0.915, Regret: 0.0045, Entropy: 0.2051
55
+ [2026-02-20T15:11:46.961494Z] Loop 38: Loss: 4.85e-02, Avg Return: 0.914, Regret: 0.0044, Entropy: 0.1906
56
+ [2026-02-20T15:11:47.886809Z] Loop 39: Loss: 4.72e-02, Avg Return: 0.915, Regret: 0.0044, Entropy: 0.1822
57
+ [2026-02-20T15:11:48.814186Z] Loop 40: Loss: 4.63e-02, Avg Return: 0.914, Regret: 0.0044, Entropy: 0.1812
58
+ [2026-02-20T15:11:49.741772Z] Loop 41: Loss: 4.59e-02, Avg Return: 0.914, Regret: 0.0043, Entropy: 0.1778
59
+ [2026-02-20T15:11:50.668009Z] Loop 42: Loss: 4.70e-02, Avg Return: 0.914, Regret: 0.0042, Entropy: 0.1887
60
+ [2026-02-20T15:11:51.594798Z] Loop 43: Loss: 5.04e-02, Avg Return: 0.914, Regret: 0.0042, Entropy: 0.1983
61
+ [2026-02-20T15:11:52.521976Z] Loop 44: Loss: 5.06e-02, Avg Return: 0.914, Regret: 0.0041, Entropy: 0.1951
62
+ [2026-02-20T15:11:53.447826Z] Loop 45: Loss: 5.25e-02, Avg Return: 0.914, Regret: 0.0042, Entropy: 0.2001
63
+ [2026-02-20T15:11:54.381269Z] Loop 46: Loss: 5.13e-02, Avg Return: 0.914, Regret: 0.0045, Entropy: 0.2037
64
+ [2026-02-20T15:11:55.307945Z] Loop 47: Loss: 5.31e-02, Avg Return: 0.913, Regret: 0.0048, Entropy: 0.2071
65
+ [2026-02-20T15:11:56.231091Z] Loop 48: Loss: 5.42e-02, Avg Return: 0.913, Regret: 0.0051, Entropy: 0.2026
66
+ [2026-02-20T15:11:57.156082Z] Loop 49: Loss: 4.99e-02, Avg Return: 0.913, Regret: 0.0057, Entropy: 0.1939
67
+ [2026-02-20T15:11:58.082806Z] Loop 50: Loss: 4.84e-02, Avg Return: 0.912, Regret: 0.0056, Entropy: 0.1874
68
+ [2026-02-20T15:11:59.007175Z] Loop 51: Loss: 4.74e-02, Avg Return: 0.912, Regret: 0.0055, Entropy: 0.1842
69
+ [2026-02-20T15:11:59.933916Z] Loop 52: Loss: 4.66e-02, Avg Return: 0.913, Regret: 0.0051, Entropy: 0.1780
70
+ [2026-02-20T15:12:00.860943Z] Loop 53: Loss: 4.69e-02, Avg Return: 0.913, Regret: 0.0048, Entropy: 0.1778
71
+ [2026-02-20T15:12:01.789070Z] Loop 54: Loss: 4.70e-02, Avg Return: 0.913, Regret: 0.0046, Entropy: 0.1745
72
+ [2026-02-20T15:12:02.717179Z] Loop 55: Loss: 4.57e-02, Avg Return: 0.913, Regret: 0.0046, Entropy: 0.1793
73
+ [2026-02-20T15:12:03.644865Z] Loop 56: Loss: 4.55e-02, Avg Return: 0.914, Regret: 0.0048, Entropy: 0.1791
74
+ [2026-02-20T15:12:04.572323Z] Loop 57: Loss: 4.63e-02, Avg Return: 0.913, Regret: 0.0049, Entropy: 0.1784
75
+ [2026-02-20T15:12:05.502437Z] Loop 58: Loss: 4.48e-02, Avg Return: 0.915, Regret: 0.0049, Entropy: 0.1755
76
+ [2026-02-20T15:12:06.432276Z] Loop 59: Loss: 4.67e-02, Avg Return: 0.914, Regret: 0.0047, Entropy: 0.1816
77
+ [2026-02-20T15:12:07.362739Z] Loop 60: Loss: 4.94e-02, Avg Return: 0.914, Regret: 0.0045, Entropy: 0.1927
78
+ [2026-02-20T15:12:08.296338Z] Loop 61: Loss: 5.24e-02, Avg Return: 0.914, Regret: 0.0044, Entropy: 0.2064
79
+ [2026-02-20T15:12:09.226059Z] Loop 62: Loss: 5.33e-02, Avg Return: 0.913, Regret: 0.0044, Entropy: 0.2052
80
+ [2026-02-20T15:12:10.156280Z] Loop 63: Loss: 5.24e-02, Avg Return: 0.914, Regret: 0.0043, Entropy: 0.2080
81
+ [2026-02-20T15:12:11.086219Z] Loop 64: Loss: 5.42e-02, Avg Return: 0.914, Regret: 0.0043, Entropy: 0.2128
82
+ [2026-02-20T15:12:12.014317Z] Loop 65: Loss: 5.33e-02, Avg Return: 0.914, Regret: 0.0042, Entropy: 0.2078
83
+ [2026-02-20T15:12:12.948136Z] Loop 66: Loss: 5.27e-02, Avg Return: 0.914, Regret: 0.0042, Entropy: 0.2046
84
+ [2026-02-20T15:12:13.876843Z] Loop 67: Loss: 5.32e-02, Avg Return: 0.915, Regret: 0.0043, Entropy: 0.2017
85
+ [2026-02-20T15:12:14.806131Z] Loop 68: Loss: 4.99e-02, Avg Return: 0.914, Regret: 0.0045, Entropy: 0.1916
86
+ [2026-02-20T15:12:15.735264Z] Loop 69: Loss: 4.94e-02, Avg Return: 0.913, Regret: 0.0048, Entropy: 0.1948
87
+ [2026-02-20T15:12:16.662876Z] Loop 70: Loss: 4.69e-02, Avg Return: 0.913, Regret: 0.0047, Entropy: 0.1813
88
+ [2026-02-20T15:12:17.590323Z] Loop 71: Loss: 5.01e-02, Avg Return: 0.914, Regret: 0.0046, Entropy: 0.1976
89
+ [2026-02-20T15:12:18.519442Z] Loop 72: Loss: 5.01e-02, Avg Return: 0.913, Regret: 0.0046, Entropy: 0.1937
90
+ [2026-02-20T15:12:19.448517Z] Loop 73: Loss: 5.09e-02, Avg Return: 0.914, Regret: 0.0045, Entropy: 0.1951
91
+ [2026-02-20T15:12:20.374411Z] Loop 74: Loss: 5.06e-02, Avg Return: 0.914, Regret: 0.0043, Entropy: 0.1943
92
+ [2026-02-20T15:12:21.303536Z] Loop 75: Loss: 5.40e-02, Avg Return: 0.915, Regret: 0.0041, Entropy: 0.2056
93
+ [2026-02-20T15:12:22.229811Z] Loop 76: Loss: 5.35e-02, Avg Return: 0.915, Regret: 0.0040, Entropy: 0.2052
94
+ [2026-02-20T15:12:23.156807Z] Loop 77: Loss: 5.27e-02, Avg Return: 0.915, Regret: 0.0039, Entropy: 0.2042
95
+ [2026-02-20T15:12:24.086553Z] Loop 78: Loss: 5.08e-02, Avg Return: 0.915, Regret: 0.0039, Entropy: 0.1980
96
+ [2026-02-20T15:12:25.014994Z] Loop 79: Loss: 4.60e-02, Avg Return: 0.915, Regret: 0.0040, Entropy: 0.1804
97
+ [2026-02-20T15:12:25.943355Z] Loop 80: Loss: 4.08e-02, Avg Return: 0.914, Regret: 0.0041, Entropy: 0.1590
98
+ [2026-02-20T15:37:36.468767Z] Loop 0: Loss: 3.85e-02, Avg Return: 0.914, Regret: 0.0043, Entropy: 0.1491
99
+ [2026-02-20T15:37:37.402566Z] Loop 1: Loss: 4.31e-02, Avg Return: 0.914, Regret: 0.0051, Entropy: 0.1655
100
+ [2026-02-20T15:37:38.329955Z] Loop 2: Loss: 4.28e-02, Avg Return: 0.913, Regret: 0.0050, Entropy: 0.1684
101
+ [2026-02-20T15:37:39.259650Z] Loop 3: Loss: 4.93e-02, Avg Return: 0.913, Regret: 0.0056, Entropy: 0.1880
102
+ [2026-02-20T15:37:40.181461Z] Loop 4: Loss: 5.50e-02, Avg Return: 0.911, Regret: 0.0074, Entropy: 0.2135
103
+ [2026-02-20T15:37:41.108236Z] Loop 5: Loss: 5.56e-02, Avg Return: 0.909, Regret: 0.0097, Entropy: 0.2237
104
+ [2026-02-20T15:37:42.035772Z] Loop 6: Loss: 5.60e-02, Avg Return: 0.910, Regret: 0.0081, Entropy: 0.2135
105
+ [2026-02-20T15:37:42.962679Z] Loop 7: Loss: 5.28e-02, Avg Return: 0.912, Regret: 0.0069, Entropy: 0.2051
106
+ [2026-02-20T15:37:43.890634Z] Loop 8: Loss: 5.08e-02, Avg Return: 0.913, Regret: 0.0059, Entropy: 0.1916
107
+ [2026-02-20T15:37:44.819100Z] Loop 9: Loss: 4.39e-02, Avg Return: 0.914, Regret: 0.0049, Entropy: 0.1635
108
+ [2026-02-20T15:37:45.744146Z] Loop 10: Loss: 4.00e-02, Avg Return: 0.913, Regret: 0.0044, Entropy: 0.1514
109
+ [2026-02-20T15:37:46.665451Z] Loop 11: Loss: 3.80e-02, Avg Return: 0.914, Regret: 0.0042, Entropy: 0.1412
110
+ [2026-02-20T15:37:47.590327Z] Loop 12: Loss: 3.70e-02, Avg Return: 0.914, Regret: 0.0042, Entropy: 0.1420
111
+ [2026-02-20T15:37:48.514048Z] Loop 13: Loss: 3.63e-02, Avg Return: 0.915, Regret: 0.0041, Entropy: 0.1425
112
+ [2026-02-20T15:37:49.441005Z] Loop 14: Loss: 3.91e-02, Avg Return: 0.914, Regret: 0.0042, Entropy: 0.1534
113
+ [2026-02-20T15:37:50.368786Z] Loop 15: Loss: 4.31e-02, Avg Return: 0.914, Regret: 0.0045, Entropy: 0.1642
114
+ [2026-02-20T15:37:51.296942Z] Loop 16: Loss: 4.88e-02, Avg Return: 0.913, Regret: 0.0052, Entropy: 0.1844
115
+ [2026-02-20T15:37:52.224480Z] Loop 17: Loss: 5.01e-02, Avg Return: 0.914, Regret: 0.0053, Entropy: 0.1920
116
+ [2026-02-20T15:37:53.153072Z] Loop 18: Loss: 4.88e-02, Avg Return: 0.913, Regret: 0.0051, Entropy: 0.1901
117
+ [2026-02-20T15:37:54.082215Z] Loop 19: Loss: 4.97e-02, Avg Return: 0.913, Regret: 0.0049, Entropy: 0.1922
118
+ [2026-02-20T15:37:55.011991Z] Loop 20: Loss: 5.16e-02, Avg Return: 0.914, Regret: 0.0049, Entropy: 0.2010
119
+ [2026-02-20T15:37:55.940529Z] Loop 21: Loss: 5.37e-02, Avg Return: 0.913, Regret: 0.0049, Entropy: 0.2068
120
+ [2026-02-20T15:37:56.866325Z] Loop 22: Loss: 5.55e-02, Avg Return: 0.913, Regret: 0.0048, Entropy: 0.2085
121
+ [2026-02-20T15:37:57.800722Z] Loop 23: Loss: 5.33e-02, Avg Return: 0.914, Regret: 0.0047, Entropy: 0.2038
122
+ [2026-02-20T15:37:58.731652Z] Loop 24: Loss: 5.47e-02, Avg Return: 0.914, Regret: 0.0047, Entropy: 0.2092
123
+ [2026-02-20T15:37:59.662698Z] Loop 25: Loss: 5.49e-02, Avg Return: 0.913, Regret: 0.0049, Entropy: 0.2113
124
+ [2026-02-20T15:38:00.594156Z] Loop 26: Loss: 5.72e-02, Avg Return: 0.913, Regret: 0.0055, Entropy: 0.2208
125
+ [2026-02-20T15:38:01.525645Z] Loop 27: Loss: 5.42e-02, Avg Return: 0.913, Regret: 0.0060, Entropy: 0.2145
126
+ [2026-02-20T15:38:02.458795Z] Loop 28: Loss: 5.51e-02, Avg Return: 0.912, Regret: 0.0062, Entropy: 0.2159
127
+ [2026-02-20T15:38:03.385399Z] Loop 29: Loss: 5.20e-02, Avg Return: 0.912, Regret: 0.0065, Entropy: 0.2093
128
+ [2026-02-20T15:38:04.310324Z] Loop 30: Loss: 5.28e-02, Avg Return: 0.912, Regret: 0.0063, Entropy: 0.2055
129
+ [2026-02-20T15:38:05.238355Z] Loop 31: Loss: 5.21e-02, Avg Return: 0.912, Regret: 0.0063, Entropy: 0.1990
130
+ [2026-02-20T15:38:06.167275Z] Loop 32: Loss: 5.07e-02, Avg Return: 0.912, Regret: 0.0062, Entropy: 0.2012
131
+ [2026-02-20T15:38:07.098818Z] Loop 33: Loss: 5.13e-02, Avg Return: 0.914, Regret: 0.0057, Entropy: 0.1989
132
+ [2026-02-20T15:38:08.029045Z] Loop 34: Loss: 5.24e-02, Avg Return: 0.913, Regret: 0.0053, Entropy: 0.2036
133
+ [2026-02-20T15:38:08.955647Z] Loop 35: Loss: 5.29e-02, Avg Return: 0.914, Regret: 0.0049, Entropy: 0.2044
134
+ [2026-02-20T15:38:09.882348Z] Loop 36: Loss: 5.40e-02, Avg Return: 0.914, Regret: 0.0047, Entropy: 0.2144
135
+ [2026-02-20T15:38:10.810467Z] Loop 37: Loss: 5.27e-02, Avg Return: 0.915, Regret: 0.0045, Entropy: 0.2051
136
+ [2026-02-20T15:38:11.759275Z] Loop 38: Loss: 4.85e-02, Avg Return: 0.914, Regret: 0.0044, Entropy: 0.1906
137
+ [2026-02-20T15:38:13.401019Z] Loop 39: Loss: 4.72e-02, Avg Return: 0.915, Regret: 0.0044, Entropy: 0.1822
138
+ [2026-02-20T15:38:14.501205Z] Loop 40: Loss: 4.63e-02, Avg Return: 0.914, Regret: 0.0044, Entropy: 0.1812
139
+ [2026-02-20T15:38:15.825281Z] Loop 41: Loss: 4.59e-02, Avg Return: 0.914, Regret: 0.0043, Entropy: 0.1778
140
+ [2026-02-20T15:38:17.891061Z] Loop 42: Loss: 4.70e-02, Avg Return: 0.914, Regret: 0.0042, Entropy: 0.1887
141
+ [2026-02-20T15:38:19.047042Z] Loop 43: Loss: 5.04e-02, Avg Return: 0.914, Regret: 0.0042, Entropy: 0.1983
142
+ [2026-02-20T15:38:20.503885Z] Loop 44: Loss: 5.06e-02, Avg Return: 0.914, Regret: 0.0041, Entropy: 0.1951
143
+ [2026-02-20T15:38:22.291765Z] Loop 45: Loss: 5.25e-02, Avg Return: 0.914, Regret: 0.0042, Entropy: 0.2001
144
+ [2026-02-20T15:38:23.703146Z] Loop 46: Loss: 5.13e-02, Avg Return: 0.914, Regret: 0.0045, Entropy: 0.2037
145
+ [2026-02-20T15:38:25.116988Z] Loop 47: Loss: 5.31e-02, Avg Return: 0.913, Regret: 0.0048, Entropy: 0.2071
146
+ [2026-02-20T15:38:26.048200Z] Loop 48: Loss: 5.42e-02, Avg Return: 0.913, Regret: 0.0051, Entropy: 0.2026
147
+ [2026-02-20T15:38:26.975435Z] Loop 49: Loss: 4.99e-02, Avg Return: 0.913, Regret: 0.0057, Entropy: 0.1939
148
+ [2026-02-20T15:38:27.903436Z] Loop 50: Loss: 4.84e-02, Avg Return: 0.912, Regret: 0.0056, Entropy: 0.1874
149
+ [2026-02-20T15:38:28.830278Z] Loop 51: Loss: 4.74e-02, Avg Return: 0.912, Regret: 0.0055, Entropy: 0.1842
150
+ [2026-02-20T15:38:29.759793Z] Loop 52: Loss: 4.66e-02, Avg Return: 0.913, Regret: 0.0051, Entropy: 0.1780
151
+ [2026-02-20T15:38:30.689577Z] Loop 53: Loss: 4.69e-02, Avg Return: 0.913, Regret: 0.0048, Entropy: 0.1778
152
+ [2026-02-20T15:38:31.619723Z] Loop 54: Loss: 4.70e-02, Avg Return: 0.913, Regret: 0.0046, Entropy: 0.1745
153
+ [2026-02-20T15:38:32.549770Z] Loop 55: Loss: 4.57e-02, Avg Return: 0.913, Regret: 0.0046, Entropy: 0.1793
154
+ [2026-02-20T15:38:33.480048Z] Loop 56: Loss: 4.55e-02, Avg Return: 0.914, Regret: 0.0048, Entropy: 0.1791
155
+ [2026-02-20T15:38:34.409414Z] Loop 57: Loss: 4.63e-02, Avg Return: 0.913, Regret: 0.0049, Entropy: 0.1784
156
+ [2026-02-20T15:38:35.338892Z] Loop 58: Loss: 4.48e-02, Avg Return: 0.915, Regret: 0.0049, Entropy: 0.1755
157
+ [2026-02-20T15:38:36.266201Z] Loop 59: Loss: 4.67e-02, Avg Return: 0.914, Regret: 0.0047, Entropy: 0.1816
158
+ [2026-02-20T15:38:37.190706Z] Loop 60: Loss: 4.94e-02, Avg Return: 0.914, Regret: 0.0045, Entropy: 0.1927
159
+ [2026-02-20T15:38:38.116569Z] Loop 61: Loss: 5.24e-02, Avg Return: 0.914, Regret: 0.0044, Entropy: 0.2064
160
+ [2026-02-20T15:38:39.040296Z] Loop 62: Loss: 5.33e-02, Avg Return: 0.913, Regret: 0.0044, Entropy: 0.2052
161
+ [2026-02-20T15:38:39.967025Z] Loop 63: Loss: 5.24e-02, Avg Return: 0.914, Regret: 0.0043, Entropy: 0.2080
162
+ [2026-02-20T15:38:40.894456Z] Loop 64: Loss: 5.42e-02, Avg Return: 0.914, Regret: 0.0043, Entropy: 0.2128
163
+ [2026-02-20T15:38:41.820519Z] Loop 65: Loss: 5.33e-02, Avg Return: 0.914, Regret: 0.0042, Entropy: 0.2078
164
+ [2026-02-20T15:38:42.745800Z] Loop 66: Loss: 5.27e-02, Avg Return: 0.914, Regret: 0.0042, Entropy: 0.2046
165
+ [2026-02-20T15:38:43.674080Z] Loop 67: Loss: 5.32e-02, Avg Return: 0.915, Regret: 0.0043, Entropy: 0.2017
166
+ [2026-02-20T15:38:44.602058Z] Loop 68: Loss: 4.99e-02, Avg Return: 0.914, Regret: 0.0045, Entropy: 0.1916
167
+ [2026-02-20T15:38:45.529723Z] Loop 69: Loss: 4.94e-02, Avg Return: 0.913, Regret: 0.0048, Entropy: 0.1948
168
+ [2026-02-20T15:38:46.458187Z] Loop 70: Loss: 4.69e-02, Avg Return: 0.913, Regret: 0.0047, Entropy: 0.1813
169
+ [2026-02-20T15:38:47.384430Z] Loop 71: Loss: 5.01e-02, Avg Return: 0.914, Regret: 0.0046, Entropy: 0.1976
170
+ [2026-02-20T15:38:48.313123Z] Loop 72: Loss: 5.01e-02, Avg Return: 0.913, Regret: 0.0046, Entropy: 0.1937
171
+ [2026-02-20T15:38:49.241927Z] Loop 73: Loss: 5.09e-02, Avg Return: 0.914, Regret: 0.0045, Entropy: 0.1951
172
+ [2026-02-20T15:38:50.169800Z] Loop 74: Loss: 5.06e-02, Avg Return: 0.914, Regret: 0.0043, Entropy: 0.1943
173
+ [2026-02-20T15:38:51.097485Z] Loop 75: Loss: 5.40e-02, Avg Return: 0.915, Regret: 0.0041, Entropy: 0.2056
174
+ [2026-02-20T15:38:52.025310Z] Loop 76: Loss: 5.35e-02, Avg Return: 0.915, Regret: 0.0040, Entropy: 0.2052
175
+ [2026-02-20T15:38:52.960718Z] Loop 77: Loss: 5.27e-02, Avg Return: 0.915, Regret: 0.0039, Entropy: 0.2042
176
+ [2026-02-20T15:38:53.888560Z] Loop 78: Loss: 5.08e-02, Avg Return: 0.915, Regret: 0.0039, Entropy: 0.1980
177
+ [2026-02-20T15:38:54.820649Z] Loop 79: Loss: 4.60e-02, Avg Return: 0.915, Regret: 0.0040, Entropy: 0.1804
178
+ [2026-02-20T15:38:55.751047Z] Loop 80: Loss: 4.08e-02, Avg Return: 0.914, Regret: 0.0041, Entropy: 0.1590