6th Push

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19530bdfe6189493527e9df6a21aba51789c3caf6d1a68cc14f499f1a9c10d24
+oid sha256:85b17e365509af3b36d08d2b53f82c080de874f7b17dc43f36356d79f1959255
 size 9879682

SoccerTwos/SoccerTwos-13499998.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19de66b2a4986b7cbfe145fe8e2452de4919b402b521235e85cea3ba89c188d4
+size 9879682

SoccerTwos/SoccerTwos-13499998.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eb4b8e2ea4d7eceffe5271f866ea4b4af3f54afe97223c6e90d65443ae8ac25
+size 126059799

SoccerTwos/SoccerTwos-13999949.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70e297c2e7fc1b631c949a5fd02b4a4cd5c4ff7c1518c14674f840c1687d696c
+size 9879682

SoccerTwos/SoccerTwos-13999949.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddaa52a3d0d206ee00e2946ae55c2805b9c82766519a7192a2794fb5e8cec2cb
+size 126059799

SoccerTwos/SoccerTwos-14499978.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f5a8cf87b90059800e7a493604b7c8869d2894d4736fe01c4159dc24bac1bca
+size 9879682

SoccerTwos/SoccerTwos-14499978.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e0e5f8a039c29ed511094845baab0d5124ff254279dca1d5ea6690f9407ebcc
+size 126059799

SoccerTwos/SoccerTwos-14999981.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85b17e365509af3b36d08d2b53f82c080de874f7b17dc43f36356d79f1959255
+size 9879682

SoccerTwos/SoccerTwos-14999981.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbd3c9c6e2455a6c8f184ae154093b448b1c826c38b0aa85bad18d4418aa5706
+size 126059799

SoccerTwos/SoccerTwos-15000100.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85b17e365509af3b36d08d2b53f82c080de874f7b17dc43f36356d79f1959255
+size 9879682

SoccerTwos/SoccerTwos-15000100.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d18d115deaa2c1773ff74246ea2c4cdcc23318842c797222a700bbec4dc75c6
+size 126059799

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dd3292a40f68b050903dbb64bcc6267c8dbca04c9dabaef84ba919d797548ae
+oid sha256:fe29e15ede30e57898d23ac2be75e8b57f2f70a4bd84ac4ff6d81613c9b264b5
 size 126058521

SoccerTwos/events.out.tfevents.1761010971.ada-B550-AORUS-ELITE.263910.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:133469ce0193e9378abb25259b84e8647e833f526ec591447fc6b17e18fbfafb
+size 1243

SoccerTwos/events.out.tfevents.1761011054.ada-B550-AORUS-ELITE.264221.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef72377c143e655adc22cdaf299320dcd8c60bd5f9dae5415823d376e72ac544
+size 5098109

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 4096, "buffer_size": 40960, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 1024, "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": 10000000, "time_horizon": 1000, "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/linux/SoccerTwos/SoccerTwos.app", "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": 4096, "buffer_size": 40960, "learning_rate": 0.0002, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 1024, "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": 15000000, "time_horizon": 1000, "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/linux/SoccerTwos/SoccerTwos.app", "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

@@ -5,7 +5,7 @@ behaviors:
     hyperparameters:
       batch_size: 4096
       buffer_size: 40960
-      learning_rate: 0.0003
+      learning_rate: 0.0002
       beta: 0.005
       epsilon: 0.2
       lambd: 0.95
@@ -37,7 +37,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 10000000
+    max_steps: 15000000
     time_horizon: 1000
     summary_freq: 10000
     threaded: false

run_logs/Player-0.log

@@ -36,7 +36,7 @@ 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: 0.550161 ms
+UnloadTime: 0.631354 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
@@ -45,7 +45,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 94118 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 94149 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
@@ -88,7 +88,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 5]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0.7 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
@@ -173,7 +173,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 8]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 0.7 KB
       Overflow Count 0
     [ALLOC_TEMP_Job.Worker 7]
       Initial Block Size 256.0 KB
@@ -231,19 +231,19 @@ 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]: 94119 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 94150 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 4.9 MB
+      Peak Allocated memory 5.0 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 94119 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 94150 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 17.3 MB
@@ -275,13 +275,13 @@ 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]: 94118 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 94149 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]: 94119 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 94150 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -293,16 +293,16 @@ 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]: 94119 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 94150 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]: 94118 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 94149 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
-      Peak Block count 1
-      Peak Allocated memory 4.0 MB
+      Peak Block count 2
+      Peak Allocated memory 4.5 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
@@ -311,13 +311,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 94119 frames
+      Peak usage frame count: [0-1.0 KB]: 94150 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]: 94118 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 94149 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": 1.6367019414901733,
-            "min": 1.5849891901016235,
-            "max": 1.9792643785476685,
+            "value": 1.5435189008712769,
+            "min": 1.4646319150924683,
+            "max": 1.6610451936721802,
             "count": 500
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 34305.2734375,
-            "min": 28913.044921875,
-            "max": 43005.05859375,
+            "value": 31759.4453125,
+            "min": 25814.9765625,
+            "max": 36021.5078125,
             "count": 500
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 48.71287128712871,
-            "min": 44.0990990990991,
-            "max": 99.02,
+            "value": 58.79761904761905,
+            "min": 42.716814159292035,
+            "max": 82.63333333333334,
             "count": 500
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19680.0,
-            "min": 18380.0,
-            "max": 20924.0,
+            "value": 19756.0,
+            "min": 18480.0,
+            "max": 20628.0,
             "count": 500
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1623.4432652326789,
-            "min": 1559.4581025612163,
-            "max": 1656.3397476316632,
+            "value": 1641.0530434980756,
+            "min": 1581.3414240873562,
+            "max": 1645.42222380018,
             "count": 500
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 327935.5395770011,
-            "min": 160354.14348183008,
-            "max": 363841.6432379561,
+            "value": 275696.9113076767,
+            "min": 194048.29977610603,
+            "max": 373368.55337094323,
             "count": 500
         },
         "SoccerTwos.Step.mean": {
-            "value": 9999954.0,
-            "min": 5009993.0,
-            "max": 9999954.0,
+            "value": 14999981.0,
+            "min": 10009960.0,
+            "max": 14999981.0,
             "count": 500
         },
         "SoccerTwos.Step.sum": {
-            "value": 9999954.0,
-            "min": 5009993.0,
-            "max": 9999954.0,
+            "value": 14999981.0,
+            "min": 10009960.0,
+            "max": 14999981.0,
             "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": -0.051841191947460175,
-            "min": -0.11536411941051483,
-            "max": 0.08685800433158875,
+            "value": -0.0025916770100593567,
+            "min": -0.11438218504190445,
+            "max": 0.07807338982820511,
             "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": -10.420079231262207,
-            "min": -18.45825958251953,
-            "max": 15.113292694091797,
+            "value": -0.4379934072494507,
+            "min": -23.128673553466797,
+            "max": 14.677797317504883,
             "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.055824413895606995,
-            "min": -0.11762833595275879,
-            "max": 0.09742508083581924,
+            "value": 0.0026981872506439686,
+            "min": -0.11424611508846283,
+            "max": 0.07508175075054169,
             "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -11.220706939697266,
-            "min": -18.820533752441406,
-            "max": 16.56226348876953,
+            "value": 0.45599365234375,
+            "min": -23.13912582397461,
+            "max": 14.11536979675293,
             "count": 500
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
@@ -86,27 +86,27 @@
             "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.011273634374438233,
-            "min": -0.31838181750340894,
-            "max": 0.3903329541737383,
+            "value": -0.02577988283168635,
+            "min": -0.3560073624359318,
+            "max": 0.2735396422578033,
             "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -2.266000509262085,
-            "min": -56.035199880599976,
-            "max": 68.69859993457794,
+            "value": -4.356800198554993,
+            "min": -58.029200077056885,
+            "max": 46.228199541568756,
             "count": 500
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.011273634374438233,
-            "min": -0.31838181750340894,
-            "max": 0.3903329541737383,
+            "value": -0.02577988283168635,
+            "min": -0.3560073624359318,
+            "max": 0.2735396422578033,
             "count": 500
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -2.266000509262085,
-            "min": -56.035199880599976,
-            "max": 68.69859993457794,
+            "value": -4.356800198554993,
+            "min": -58.029200077056885,
+            "max": 46.228199541568756,
             "count": 500
         },
         "SoccerTwos.IsTraining.mean": {
@@ -122,51 +122,51 @@
             "count": 500
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.013145445519573211,
-            "min": 0.008717801532475278,
-            "max": 0.016552267402100068,
+            "value": 0.012675322993891314,
+            "min": 0.008311386445226769,
+            "max": 0.016500145032963095,
             "count": 121
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.013145445519573211,
-            "min": 0.008717801532475278,
-            "max": 0.016552267402100068,
+            "value": 0.012675322993891314,
+            "min": 0.008311386445226769,
+            "max": 0.016500145032963095,
             "count": 121
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.12003865043322245,
-            "min": 0.09207618981599808,
-            "max": 0.12968844001491864,
+            "value": 0.12124239106973013,
+            "min": 0.10481940135359764,
+            "max": 0.1345561275879542,
             "count": 121
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.12003865043322245,
-            "min": 0.09207618981599808,
-            "max": 0.12968844001491864,
+            "value": 0.12124239106973013,
+            "min": 0.10481940135359764,
+            "max": 0.1345561275879542,
             "count": 121
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.12265782281756402,
-            "min": 0.09331686571240425,
-            "max": 0.13381266643603643,
+            "value": 0.12398228074113528,
+            "min": 0.10591413453221321,
+            "max": 0.1369128222266833,
             "count": 121
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.12265782281756402,
-            "min": 0.09331686571240425,
-            "max": 0.13381266643603643,
+            "value": 0.12398228074113528,
+            "min": 0.10591413453221321,
+            "max": 0.1369128222266833,
             "count": 121
         },
         "SoccerTwos.Policy.LearningRate.mean": {
-            "value": 0.0003,
-            "min": 0.0003,
-            "max": 0.0003,
+            "value": 0.00019999999999999996,
+            "min": 0.00019999999999999996,
+            "max": 0.00019999999999999996,
             "count": 121
         },
         "SoccerTwos.Policy.LearningRate.sum": {
-            "value": 0.0003,
-            "min": 0.0003,
-            "max": 0.0003,
+            "value": 0.00019999999999999996,
+            "min": 0.00019999999999999996,
+            "max": 0.00019999999999999996,
             "count": 121
         },
         "SoccerTwos.Policy.Epsilon.mean": {
@@ -196,7 +196,7 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1760996306",
+        "start_time_seconds": "1761011053",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
         "command_line_arguments": "/home/ada/work/ai/venv3.10/bin/mlagents-learn ./config/poca/SoccerTwosGo.yaml --resume --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics",
         "mlagents_version": "1.2.0.dev0",
@@ -204,59 +204,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.9.0+cu128",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1761004055"
+        "end_time_seconds": "1761019758"
     },
-    "total": 7748.330938450003,
+    "total": 8704.57901644602,
     "count": 1,
-    "self": 0.26921172501170076,
+    "self": 0.9726788210100494,
     "children": {
         "run_training.setup": {
-            "total": 0.023466141981771216,
+            "total": 0.024575264018494636,
             "count": 1,
-            "self": 0.023466141981771216
+            "self": 0.024575264018494636
         },
         "TrainerController.start_learning": {
-            "total": 7748.038260583009,
+            "total": 8703.581762360991,
             "count": 1,
-            "self": 5.618356353603303,
+            "self": 7.502892200194765,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.3384398269699886,
+                    "total": 2.129385295906104,
                     "count": 26,
-                    "self": 2.3384398269699886
+                    "self": 2.129385295906104
                 },
                 "TrainerController.advance": {
-                    "total": 7738.062682880438,
-                    "count": 345799,
-                    "self": 5.045579213445308,
+                    "total": 8691.612080165913,
+                    "count": 347303,
+                    "self": 6.230914909858257,
                     "children": {
                         "env_step": {
-                            "total": 6082.852147460682,
-                            "count": 345799,
-                            "self": 4709.581325814157,
+                            "total": 6704.959744712687,
+                            "count": 347303,
+                            "self": 5021.182745416998,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 1369.6413307468465,
-                                    "count": 345799,
-                                    "self": 27.880579809192568,
+                                    "total": 1678.7599376246217,
+                                    "count": 347303,
+                                    "self": 39.04678861272987,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 1341.760750937654,
-                                            "count": 627462,
-                                            "self": 1341.760750937654
+                                            "total": 1639.7131490118918,
+                                            "count": 627670,
+                                            "self": 1639.7131490118918
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 3.6294908996787854,
-                                    "count": 345799,
+                                    "total": 5.017061671067495,
+                                    "count": 347303,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 7732.097283148003,
-                                            "count": 345799,
+                                            "total": 8685.496602965024,
+                                            "count": 347303,
                                             "is_parallel": true,
-                                            "self": 3657.1457496463845,
+                                            "self": 4470.667818740127,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -265,48 +265,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0019191680185031146,
+                                                            "total": 0.002683888975298032,
                                                             "count": 2,
                                                             "is_parallel": true,
-                                                            "self": 0.0004621940024662763,
+                                                            "self": 0.000585997971938923,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0014569740160368383,
+                                                                    "total": 0.002097891003359109,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0014569740160368383
+                                                                    "self": 0.002097891003359109
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.019876411010045558,
+                                                            "total": 0.021987969987094402,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0004738760180771351,
+                                                            "self": 0.0004761809832416475,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0007193349883891642,
+                                                                    "total": 0.00046435699914582074,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0007193349883891642
+                                                                    "self": 0.00046435699914582074
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.01740247299312614,
+                                                                    "total": 0.01973794001969509,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.01740247299312614
+                                                                    "self": 0.01973794001969509
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0012807270104531199,
+                                                                    "total": 0.0013094919850118458,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00022227209410630167,
+                                                                    "self": 0.00024246098473668098,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0010584549163468182,
+                                                                            "total": 0.0010670310002751648,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0010584549163468182
+                                                                            "self": 0.0010670310002751648
                                                                         }
                                                                     }
                                                                 }
@@ -315,48 +315,48 @@
                                                     }
                                                 },
                                                 "steps_from_proto": {
-                                                    "total": 0.05414839289733209,
+                                                    "total": 0.05173607706092298,
                                                     "count": 50,
                                                     "is_parallel": true,
-                                                    "self": 0.008624403737485409,
+                                                    "self": 0.008709836401976645,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.04552398915984668,
+                                                            "total": 0.043026240658946335,
                                                             "count": 200,
                                                             "is_parallel": true,
-                                                            "self": 0.04552398915984668
+                                                            "self": 0.043026240658946335
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 4074.897385108721,
-                                                    "count": 345798,
+                                                    "total": 4214.7770481478365,
+                                                    "count": 347302,
                                                     "is_parallel": true,
-                                                    "self": 252.111800251354,
+                                                    "self": 237.83366664528148,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 167.6272666262812,
-                                                            "count": 345798,
+                                                            "total": 162.09566081810044,
+                                                            "count": 347302,
                                                             "is_parallel": true,
-                                                            "self": 167.6272666262812
+                                                            "self": 162.09566081810044
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 2987.5401724322,
-                                                            "count": 345798,
+                                                            "total": 3184.5067745028355,
+                                                            "count": 347302,
                                                             "is_parallel": true,
-                                                            "self": 2987.5401724322
+                                                            "self": 3184.5067745028355
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 667.618145798886,
-                                                            "count": 691596,
+                                                            "total": 630.3409461816191,
+                                                            "count": 694604,
                                                             "is_parallel": true,
-                                                            "self": 109.95982521731639,
+                                                            "self": 106.73629873536993,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 557.6583205815696,
-                                                                    "count": 2766384,
+                                                                    "total": 523.6046474462491,
+                                                                    "count": 2778416,
                                                                     "is_parallel": true,
-                                                                    "self": 557.6583205815696
+                                                                    "self": 523.6046474462491
                                                                 }
                                                             }
                                                         }
@@ -369,31 +369,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 1650.1649562063103,
-                            "count": 345799,
-                            "self": 43.24377060693223,
+                            "total": 1980.4214205433673,
+                            "count": 347303,
+                            "self": 60.59123472208739,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 766.3849045703828,
-                                    "count": 345799,
-                                    "self": 743.9896677544166,
+                                    "total": 951.9022839034442,
+                                    "count": 347303,
+                                    "self": 928.9015034834156,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 22.3952368159662,
+                                            "total": 23.000780420028605,
                                             "count": 10,
-                                            "self": 22.3952368159662
+                                            "self": 23.000780420028605
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 840.5362810289953,
+                                    "total": 967.9279019178357,
                                     "count": 121,
-                                    "self": 486.3395080231712,
+                                    "self": 540.7814483185066,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 354.19677300582407,
+                                            "total": 427.1464535993291,
                                             "count": 3630,
-                                            "self": 354.19677300582407
+                                            "self": 427.1464535993291
                                         }
                                     }
                                 }
@@ -402,19 +402,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 5.309993866831064e-07,
+                    "total": 5.709880497306585e-07,
                     "count": 1,
-                    "self": 5.309993866831064e-07
+                    "self": 5.709880497306585e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 2.0187809909984935,
+                    "total": 2.33740412798943,
                     "count": 1,
-                    "self": 0.05161439499352127,
+                    "self": 0.15179298998555169,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 1.9671665960049722,
+                            "total": 2.1856111380038783,
                             "count": 1,
-                            "self": 1.9671665960049722
+                            "self": 2.1856111380038783
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,59 +2,59 @@
     "SoccerTwos": {
         "checkpoints": [
             {
-                "steps": 8499976,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8499976.onnx",
+                "steps": 13499998,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-13499998.onnx",
                 "reward": 0.0,
-                "creation_time": 1761001715.182635,
+                "creation_time": 1761017130.512117,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8499976.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-13499998.pt"
                 ]
             },
             {
-                "steps": 8999998,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8999998.onnx",
+                "steps": 13999949,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-13999949.onnx",
                 "reward": 0.0,
-                "creation_time": 1761002493.437252,
+                "creation_time": 1761018000.4892576,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8999998.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-13999949.pt"
                 ]
             },
             {
-                "steps": 9499832,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-9499832.onnx",
+                "steps": 14499978,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-14499978.onnx",
                 "reward": 0.0,
-                "creation_time": 1761003273.377863,
+                "creation_time": 1761018879.4497623,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-9499832.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-14499978.pt"
                 ]
             },
             {
-                "steps": 9999954,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-9999954.onnx",
+                "steps": 14999981,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-14999981.onnx",
                 "reward": 0.0,
-                "creation_time": 1761004052.7025542,
+                "creation_time": 1761019755.1594071,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-9999954.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-14999981.pt"
                 ]
             },
             {
-                "steps": 10000056,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-10000056.onnx",
+                "steps": 15000100,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-15000100.onnx",
                 "reward": 0.0,
-                "creation_time": 1761004054.6789157,
+                "creation_time": 1761019757.3593361,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-10000056.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-15000100.pt"
                 ]
             }
         ],
-        "elo": 1628.0153703421813,
+        "elo": 1640.8048437359187,
         "final_checkpoint": {
-            "steps": 10000056,
+            "steps": 15000100,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1761004054.6789157,
+            "creation_time": 1761019757.3593361,
             "auxillary_file_paths": [
-                "results/SoccerTwos/SoccerTwos/SoccerTwos-10000056.pt"
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-15000100.pt"
             ]
         }
     },