4M steps

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10b1211d7523e4b4dfa697ef7d6789dfbc18c3530210aa017f59eb0d0e6b1358
+oid sha256:9d19979a6c74f3f6a781d1e12bc1c3fc9c275ed185f423dd4ec9b5efac43cdd2
 size 2820313

SoccerTwos/SoccerTwos-3499958.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:225e046f0bb5fdffbf5b5d27988de24a13a5fd6f23e96864a8a49a2b0c5bcf03
+size 2820313

SoccerTwos/SoccerTwos-3499958.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32c55d6543f8930b9fa63c221b53fd103398e98f8545377db7dadd2f10880d9c
+size 34740902

SoccerTwos/SoccerTwos-3999748.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d19979a6c74f3f6a781d1e12bc1c3fc9c275ed185f423dd4ec9b5efac43cdd2
+size 2820313

SoccerTwos/SoccerTwos-3999748.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee3444749d59e76bc01adde72e2269abdec29dca3d1ef5c45975f5d23ff2b0ec
+size 34740902

SoccerTwos/SoccerTwos-4000084.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d19979a6c74f3f6a781d1e12bc1c3fc9c275ed185f423dd4ec9b5efac43cdd2
+size 2820313

SoccerTwos/SoccerTwos-4000084.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51c051e3c6230da5fcd27207fff2dad402d112f26d5ba4b1fdd87bfac7adc2fb
+size 34740902

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ed3ccd221f974a7494ee3d2c5807b971d693136a0c902b48843cee42020fa69
+oid sha256:99ebe9e952fde5a549c3d3500d5b5d8cdf308bbff706cf8c316207083204e89d
 size 34739782

SoccerTwos/events.out.tfevents.1718279493.5450768f0a05.12964.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:483cbfe3b4da1774361e3a7a6fadbe93f963bcfb539234070e351d064dd059c1
+size 1045456

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 1024, "buffer_size": 10240, "learning_rate": 0.0001, "beta": 0.01, "epsilon": 0.3, "lambd": 0.95, "num_epoch": 6, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 3000000, "time_horizon": 2048, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "training-envs-executables/SoccerTwos/SoccerTwos.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 1024, "buffer_size": 10240, "learning_rate": 0.0001, "beta": 0.01, "epsilon": 0.3, "lambd": 0.95, "num_epoch": 6, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 4000000, "time_horizon": 2048, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "training-envs-executables/SoccerTwos/SoccerTwos.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -37,7 +37,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 3000000
+    max_steps: 4000000
     time_horizon: 2048
     summary_freq: 10000
     threaded: false

run_logs/Player-0.log

@@ -31,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.082 seconds
+- Completed reload, in  0.081 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -56,7 +56,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.718161 ms
+UnloadTime: 0.671783 ms
 Registered Communicator in Agent.
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
@@ -65,7 +65,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 18835 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 18858 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.1 MB
@@ -181,22 +181,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 3
+  Peak main deferred allocation count 2
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 18836 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 18859 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 5.1 MB
+      Peak Allocated memory 4.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18836 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18859 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.1 MB
+      Peak Allocated memory 17.6 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -225,13 +225,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18835 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18858 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 65.6 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [128.0 KB-256.0 KB]: 18836 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 18859 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -243,13 +243,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 18836 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 18859 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 0.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 18835 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 18858 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.5 MB
@@ -261,13 +261,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18836 frames
+      Peak usage frame count: [0-1.0 KB]: 18859 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [1.0 KB-2.0 KB]: 18835 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18858 frames, [2.0 KB-4.0 KB]: 1 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 2.2 KB

run_logs/timers.json

@@ -2,75 +2,75 @@
     "name": "root",
     "gauges": {
         "SoccerTwos.Policy.Entropy.mean": {
-            "value": 2.201995611190796,
-            "min": 2.173480272293091,
-            "max": 2.314014196395874,
+            "value": 2.223773241043091,
+            "min": 2.0722453594207764,
+            "max": 2.236091136932373,
             "count": 100
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 44674.0859375,
-            "min": 37297.90234375,
-            "max": 52114.0,
+            "value": 45258.234375,
+            "min": 38056.3828125,
+            "max": 50514.96875,
             "count": 100
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 65.52054794520548,
-            "min": 54.666666666666664,
-            "max": 93.9423076923077,
+            "value": 77.578125,
+            "min": 51.44086021505376,
+            "max": 87.10344827586206,
             "count": 100
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19132.0,
-            "min": 18736.0,
-            "max": 20684.0,
+            "value": 19860.0,
+            "min": 18568.0,
+            "max": 20516.0,
             "count": 100
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1501.2977191837756,
-            "min": 1448.428316190716,
-            "max": 1503.7782581484385,
+            "value": 1488.8218073264109,
+            "min": 1468.8339752147765,
+            "max": 1508.8299624178053,
             "count": 100
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 219189.46700083124,
-            "min": 147811.67781677181,
-            "max": 279689.9748241801,
+            "value": 190569.1913377806,
+            "min": 172079.39408491494,
+            "max": 276200.57098956243,
             "count": 100
         },
         "SoccerTwos.Step.mean": {
-            "value": 2999970.0,
-            "min": 2009991.0,
-            "max": 2999970.0,
+            "value": 3999748.0,
+            "min": 3009969.0,
+            "max": 3999748.0,
             "count": 100
         },
         "SoccerTwos.Step.sum": {
-            "value": 2999970.0,
-            "min": 2009991.0,
-            "max": 2999970.0,
+            "value": 3999748.0,
+            "min": 3009969.0,
+            "max": 3999748.0,
             "count": 100
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": -0.07235688716173172,
-            "min": -0.1096392348408699,
-            "max": 0.09858974814414978,
+            "value": -0.0115288607776165,
+            "min": -0.1206521987915039,
+            "max": 0.09617013484239578,
             "count": 100
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": -10.564105987548828,
-            "min": -15.104362487792969,
-            "max": 14.196924209594727,
+            "value": -1.475694179534912,
+            "min": -20.629596710205078,
+            "max": 17.022113800048828,
             "count": 100
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.07161447405815125,
-            "min": -0.10906262695789337,
-            "max": 0.10088992118835449,
+            "value": -0.015976352617144585,
+            "min": -0.12377264350652695,
+            "max": 0.10104299336671829,
             "count": 100
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -10.455713272094727,
-            "min": -14.786467552185059,
-            "max": 14.528148651123047,
+            "value": -2.044973134994507,
+            "min": -21.404094696044922,
+            "max": 17.88460922241211,
             "count": 100
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
@@ -86,27 +86,27 @@
             "count": 100
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.07710684897148445,
-            "min": -0.42398394241820286,
-            "max": 0.2856749995715088,
+            "value": -0.03146406123414636,
+            "min": -0.27117222133609986,
+            "max": 0.32952272575913055,
             "count": 100
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -11.257599949836731,
-            "min": -58.08580011129379,
-            "max": 41.13719993829727,
+            "value": -4.027399837970734,
+            "min": -46.406399846076965,
+            "max": 43.49699980020523,
             "count": 100
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.07710684897148445,
-            "min": -0.42398394241820286,
-            "max": 0.2856749995715088,
+            "value": -0.03146406123414636,
+            "min": -0.27117222133609986,
+            "max": 0.32952272575913055,
             "count": 100
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -11.257599949836731,
-            "min": -58.08580011129379,
-            "max": 41.13719993829727,
+            "value": -4.027399837970734,
+            "min": -46.406399846076965,
+            "max": 43.49699980020523,
             "count": 100
         },
         "SoccerTwos.IsTraining.mean": {
@@ -122,39 +122,39 @@
             "count": 100
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.020043744097711168,
-            "min": 0.017251228770085923,
-            "max": 0.03185359615987788,
+            "value": 0.026185355508156743,
+            "min": 0.020323997944554625,
+            "max": 0.03133109582704492,
             "count": 96
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.020043744097711168,
-            "min": 0.017251228770085923,
-            "max": 0.03185359615987788,
+            "value": 0.026185355508156743,
+            "min": 0.020323997944554625,
+            "max": 0.03133109582704492,
             "count": 96
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.1033657560745875,
-            "min": 0.0701694172496597,
-            "max": 0.1033657560745875,
+            "value": 0.08392822475483021,
+            "min": 0.08149543609470129,
+            "max": 0.1144369309147199,
             "count": 96
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.1033657560745875,
-            "min": 0.0701694172496597,
-            "max": 0.1033657560745875,
+            "value": 0.08392822475483021,
+            "min": 0.08149543609470129,
+            "max": 0.1144369309147199,
             "count": 96
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.10660624156395594,
-            "min": 0.07164305417488019,
-            "max": 0.10660624156395594,
+            "value": 0.08637854494154454,
+            "min": 0.08300136315325896,
+            "max": 0.11914086317022642,
             "count": 96
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.10660624156395594,
-            "min": 0.07164305417488019,
-            "max": 0.10660624156395594,
+            "value": 0.08637854494154454,
+            "min": 0.08300136315325896,
+            "max": 0.11914086317022642,
             "count": 96
         },
         "SoccerTwos.Policy.LearningRate.mean": {
@@ -196,7 +196,7 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1718276835",
+        "start_time_seconds": "1718279492",
         "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn config/poca/SoccerTwos.yaml --env=training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume",
         "mlagents_version": "1.1.0.dev0",
@@ -204,59 +204,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.3.0+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1718279378"
+        "end_time_seconds": "1718282010"
     },
-    "total": 2543.1800257669997,
+    "total": 2517.969767197,
     "count": 1,
-    "self": 0.4459229669996603,
+    "self": 0.43776554199985185,
     "children": {
         "run_training.setup": {
-            "total": 0.051663405999988754,
+            "total": 0.0542554039998322,
             "count": 1,
-            "self": 0.051663405999988754
+            "self": 0.0542554039998322
         },
         "TrainerController.start_learning": {
-            "total": 2542.682439394,
+            "total": 2517.477746251,
             "count": 1,
-            "self": 1.7609745530094187,
+            "self": 1.6043100350693749,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.4089116700005206,
+                    "total": 2.372079333999409,
                     "count": 6,
-                    "self": 2.4089116700005206
+                    "self": 2.372079333999409
                 },
                 "TrainerController.advance": {
-                    "total": 2538.2034783439904,
-                    "count": 68323,
-                    "self": 1.7323525409487956,
+                    "total": 2513.2097595329315,
+                    "count": 68847,
+                    "self": 1.6440261898642348,
                     "children": {
                         "env_step": {
-                            "total": 1754.4153196360703,
-                            "count": 68323,
-                            "self": 1334.566942097061,
+                            "total": 1719.6449874930577,
+                            "count": 68847,
+                            "self": 1312.8831236869564,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 418.84384843703094,
-                                    "count": 68323,
-                                    "self": 12.063535462993457,
+                                    "total": 405.8213756830296,
+                                    "count": 68847,
+                                    "self": 9.936953617958352,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 406.7803129740375,
-                                            "count": 125570,
-                                            "self": 406.7803129740375
+                                            "total": 395.88442206507125,
+                                            "count": 125724,
+                                            "self": 395.88442206507125
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 1.0045291019783917,
-                                    "count": 68323,
+                                    "total": 0.9404881230716455,
+                                    "count": 68847,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2537.1526747409644,
-                                            "count": 68323,
+                                            "total": 2512.8244949230334,
+                                            "count": 68847,
                                             "is_parallel": true,
-                                            "self": 1416.4915292459632,
+                                            "self": 1408.677215260032,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -265,48 +265,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0033443359999978384,
+                                                            "total": 0.003062387000227318,
                                                             "count": 2,
                                                             "is_parallel": true,
-                                                            "self": 0.0008517240000287529,
+                                                            "self": 0.000803287000508135,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0024926119999690854,
+                                                                    "total": 0.002259099999719183,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0024926119999690854
+                                                                    "self": 0.002259099999719183
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.03887877500000059,
+                                                            "total": 0.03823810899984892,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0011581419999515674,
+                                                            "self": 0.00118418300007761,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0008241240000188554,
+                                                                    "total": 0.0008255600000666163,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0008241240000188554
+                                                                    "self": 0.0008255600000666163
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.03348753300002727,
+                                                                    "total": 0.03281173899995338,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.03348753300002727
+                                                                    "self": 0.03281173899995338
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0034089760000028946,
+                                                                    "total": 0.0034166269997513155,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005874099998095517,
+                                                                    "self": 0.0007046189994071028,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.002821566000193343,
+                                                                            "total": 0.0027120080003442126,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.002821566000193343
+                                                                            "self": 0.0027120080003442126
                                                                         }
                                                                     }
                                                                 }
@@ -315,48 +315,48 @@
                                                     }
                                                 },
                                                 "steps_from_proto": {
-                                                    "total": 0.009957218000010926,
+                                                    "total": 0.01150233199905415,
                                                     "count": 10,
                                                     "is_parallel": true,
-                                                    "self": 0.0020800090006787286,
+                                                    "self": 0.0023311429945351847,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.007877208999332197,
+                                                            "total": 0.009171189004518965,
                                                             "count": 40,
                                                             "is_parallel": true,
-                                                            "self": 0.007877208999332197
+                                                            "self": 0.009171189004518965
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1120.6511882770012,
-                                                    "count": 68322,
+                                                    "total": 1104.1357773310024,
+                                                    "count": 68846,
                                                     "is_parallel": true,
-                                                    "self": 69.13649921701744,
+                                                    "self": 68.31497311213025,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 45.612905000973626,
-                                                            "count": 68322,
+                                                            "total": 46.387385405968416,
+                                                            "count": 68846,
                                                             "is_parallel": true,
-                                                            "self": 45.612905000973626
+                                                            "self": 46.387385405968416
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 788.4737009670148,
-                                                            "count": 68322,
+                                                            "total": 773.3335762869528,
+                                                            "count": 68846,
                                                             "is_parallel": true,
-                                                            "self": 788.4737009670148
+                                                            "self": 773.3335762869528
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 217.42808309199535,
-                                                            "count": 136644,
+                                                            "total": 216.09984252595086,
+                                                            "count": 137692,
                                                             "is_parallel": true,
-                                                            "self": 36.7278482309996,
+                                                            "self": 36.31782842980056,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 180.70023486099575,
-                                                                    "count": 546576,
+                                                                    "total": 179.7820140961503,
+                                                                    "count": 550768,
                                                                     "is_parallel": true,
-                                                                    "self": 180.70023486099575
+                                                                    "self": 179.7820140961503
                                                                 }
                                                             }
                                                         }
@@ -369,31 +369,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 782.0558061669711,
-                            "count": 68323,
-                            "self": 12.882832155030542,
+                            "total": 791.9207458500096,
+                            "count": 68847,
+                            "self": 12.895249707110906,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 215.49916042294052,
-                                    "count": 68323,
-                                    "self": 214.983963919941,
+                                    "total": 225.82177020290283,
+                                    "count": 68847,
+                                    "self": 225.14665546390233,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.5151965029995154,
+                                            "total": 0.6751147390004917,
                                             "count": 2,
-                                            "self": 0.5151965029995154
+                                            "self": 0.6751147390004917
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 553.673813589,
+                                    "total": 553.2037259399958,
                                     "count": 96,
-                                    "self": 299.7714528620177,
+                                    "self": 297.6213310639955,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 253.9023607269823,
+                                            "total": 255.5823948760003,
                                             "count": 5760,
-                                            "self": 253.9023607269823
+                                            "self": 255.5823948760003
                                         }
                                     }
                                 }
@@ -402,19 +402,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 8.130000423989259e-07,
+                    "total": 9.069999578059651e-07,
                     "count": 1,
-                    "self": 8.130000423989259e-07
+                    "self": 9.069999578059651e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.3090740139996342,
+                    "total": 0.2915964419999,
                     "count": 1,
-                    "self": 0.0040466209998157865,
+                    "self": 0.0039638009993723244,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.3050273929998184,
+                            "total": 0.28763264100052766,
                             "count": 1,
-                            "self": 0.3050273929998184
+                            "self": 0.28763264100052766
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,59 +2,59 @@
     "SoccerTwos": {
         "checkpoints": [
             {
-                "steps": 1999965,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-1999965.onnx",
+                "steps": 2999970,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-2999970.onnx",
                 "reward": 0.0,
-                "creation_time": 1718194235.8215587,
+                "creation_time": 1718279377.628169,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-1999965.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-2999970.pt"
                 ]
             },
             {
-                "steps": 2000290,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-2000290.onnx",
+                "steps": 3000068,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3000068.onnx",
                 "reward": 0.0,
-                "creation_time": 1718194236.2838733,
+                "creation_time": 1718279377.951402,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-2000290.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-3000068.pt"
                 ]
             },
             {
-                "steps": 2499995,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-2499995.onnx",
+                "steps": 3499958,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3499958.onnx",
                 "reward": 0.0,
-                "creation_time": 1718278133.4389424,
+                "creation_time": 1718280764.2535863,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-2499995.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-3499958.pt"
                 ]
             },
             {
-                "steps": 2999970,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-2999970.onnx",
+                "steps": 3999748,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3999748.onnx",
                 "reward": 0.0,
-                "creation_time": 1718279377.628169,
+                "creation_time": 1718282009.9757707,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-2999970.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-3999748.pt"
                 ]
             },
             {
-                "steps": 3000068,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3000068.onnx",
+                "steps": 4000084,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-4000084.onnx",
                 "reward": 0.0,
-                "creation_time": 1718279377.951402,
+                "creation_time": 1718282010.2985783,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-3000068.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-4000084.pt"
                 ]
             }
         ],
-        "elo": 1495.8915224153673,
+        "elo": 1489.2215205434777,
         "final_checkpoint": {
-            "steps": 3000068,
+            "steps": 4000084,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1718279377.951402,
+            "creation_time": 1718282010.2985783,
             "auxillary_file_paths": [
-                "results/SoccerTwos/SoccerTwos/SoccerTwos-3000068.pt"
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-4000084.pt"
             ]
         }
     },