7M steps

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e676dd6d074cfcc8a945a987063c776bba8def9aec143efe544091ba6bce9c6b
+oid sha256:df31e7eaa1c9dc0ce2630bc04be97af5a30cf137edd6656c45b236774f466347
 size 2820313

SoccerTwos/SoccerTwos-5499958.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4deebf5846def2640cb9bc21a1a0e3dec8a418ebf26649c6af7af1819a2f0c33
+size 2820313

SoccerTwos/SoccerTwos-5499958.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8e0c597f1d70e3d21b6fdf13d8016c3fa66e5d64676bfd3537847b535b529ea
+size 34740902

SoccerTwos/SoccerTwos-5999962.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25c7650f6dc7d12f5d62dcedd8313f75a2defd8bf9f2aca159192e1ffb559283
+size 2820313

SoccerTwos/SoccerTwos-5999962.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6f2c7a17f5fcabacdf52349731b91e995d323a16b35982891d1c31a4a6e05a6
+size 34740902

SoccerTwos/SoccerTwos-6499901.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:733089b6a83bf7d0a8ba47748b4745eb8ba1b68fad03e8e9ee9ff9ff9e3edfa9
+size 2820313

SoccerTwos/SoccerTwos-6499901.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e6d8600e9ed481182b816cd886e066d0b23db3aa5dd502e00873d0dca21e76f
+size 34740902

SoccerTwos/SoccerTwos-6999977.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df31e7eaa1c9dc0ce2630bc04be97af5a30cf137edd6656c45b236774f466347
+size 2820313

SoccerTwos/SoccerTwos-6999977.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be360b0533fee54d0f99f13309946975021dc401b77b1b84ec3f128b261f5106
+size 34740902

SoccerTwos/SoccerTwos-7000094.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df31e7eaa1c9dc0ce2630bc04be97af5a30cf137edd6656c45b236774f466347
+size 2820313

SoccerTwos/SoccerTwos-7000094.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:800427acef877270a957d9609fb94dacf4c2cf1cc2687b79fc1f31092223735e
+size 34740902

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c567ea842f38b762c58f1d3f2ebcf0574e6cc509f0397b6cdca983855e1b2c6f
+oid sha256:6c7f7a5b3c8ee9065e39d7c6fb908c5f14432f5823eb48307da0861815f45870
 size 34739782

SoccerTwos/events.out.tfevents.1718522800.412f5050b3f8.3323.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83134f4b34ead5455d33407cd4e999214deccabaeaebf13f9a730599e742e5c0
+size 2090018

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": 5000000, "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": 7000000, "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: 5000000
+    max_steps: 7000000
     time_horizon: 2048
     summary_freq: 10000
     threaded: false

run_logs/Player-0.log

@@ -34,7 +34,7 @@ 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  0.097 seconds
+- Completed reload, in  0.084 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)
@@ -59,7 +59,7 @@ 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: 0.721597 ms
+UnloadTime: 0.699797 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
@@ -68,7 +68,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 18827 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 37673 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
@@ -184,19 +184,19 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 2
+  Peak main deferred allocation count 3
     [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]: 18828 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 37674 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       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]: 18828 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 37674 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 17.6 MB
@@ -228,13 +228,13 @@ 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]: 18827 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 37673 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]: 18828 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 37674 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -246,13 +246,13 @@ 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]: 18828 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 37674 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]: 18827 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 37673 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
@@ -264,13 +264,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18828 frames
+      Peak usage frame count: [0-1.0 KB]: 37674 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]: 18827 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 37673 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

@@ -2,201 +2,201 @@
     "name": "root",
     "gauges": {
         "SoccerTwos.Policy.Entropy.mean": {
-            "value": 2.1875576972961426,
-            "min": 2.144973039627075,
-            "max": 2.2713446617126465,
-            "count": 100
+            "value": 2.1015546321868896,
+            "min": 1.9260947704315186,
+            "max": 2.2162485122680664,
+            "count": 200
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 45571.203125,
-            "min": 34911.1328125,
-            "max": 50452.00390625,
-            "count": 100
+            "value": 40013.6015625,
+            "min": 36403.37890625,
+            "max": 48694.53125,
+            "count": 200
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 70.14285714285714,
-            "min": 55.79545454545455,
-            "max": 105.46808510638297,
-            "count": 100
+            "value": 67.5774647887324,
+            "min": 49.686868686868685,
+            "max": 98.2,
+            "count": 200
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19640.0,
-            "min": 19072.0,
-            "max": 20416.0,
-            "count": 100
+            "value": 19192.0,
+            "min": 18508.0,
+            "max": 20980.0,
+            "count": 200
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1475.7673077529762,
-            "min": 1455.5852748018806,
-            "max": 1495.4709782409363,
-            "count": 100
+            "value": 1501.2183115300984,
+            "min": 1458.23807506226,
+            "max": 1542.6958683603368,
+            "count": 200
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 206607.42308541667,
-            "min": 138573.4318195411,
-            "max": 258146.97528522566,
-            "count": 100
+            "value": 213173.00023727398,
+            "min": 152618.49962697105,
+            "max": 299146.18093298224,
+            "count": 200
         },
         "SoccerTwos.Step.mean": {
-            "value": 4999989.0,
-            "min": 4009955.0,
-            "max": 4999989.0,
-            "count": 100
+            "value": 6999977.0,
+            "min": 5009884.0,
+            "max": 6999977.0,
+            "count": 200
         },
         "SoccerTwos.Step.sum": {
-            "value": 4999989.0,
-            "min": 4009955.0,
-            "max": 4999989.0,
-            "count": 100
+            "value": 6999977.0,
+            "min": 5009884.0,
+            "max": 6999977.0,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": -0.008360597304999828,
-            "min": -0.13213926553726196,
-            "max": 0.047096967697143555,
-            "count": 100
+            "value": -0.021804125979542732,
+            "min": -0.16370217502117157,
+            "max": 0.09212000668048859,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": -1.1704835891723633,
-            "min": -19.013656616210938,
-            "max": 6.358090400695801,
-            "count": 100
+            "value": -3.117990016937256,
+            "min": -22.918304443359375,
+            "max": 12.161711692810059,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.005427720490843058,
-            "min": -0.13081811368465424,
-            "max": 0.04446444660425186,
-            "count": 100
+            "value": -0.021971693262457848,
+            "min": -0.16531510651111603,
+            "max": 0.09050528705120087,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -0.7598809003829956,
-            "min": -19.144575119018555,
-            "max": 6.002700328826904,
-            "count": 100
+            "value": -3.1419520378112793,
+            "min": -23.144115447998047,
+            "max": 12.065362930297852,
+            "count": 200
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 100
+            "count": 200
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 100
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": 0.07113428797040666,
-            "min": -0.37446071580052376,
-            "max": 0.30961999893188474,
-            "count": 100
+            "value": -0.116802798701333,
+            "min": -0.31984999863540425,
+            "max": 0.2896556258201599,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": 9.958800315856934,
-            "min": -41.93960016965866,
-            "max": 37.15439987182617,
-            "count": 100
+            "value": -16.70280021429062,
+            "min": -43.49959981441498,
+            "max": 43.73799949884415,
+            "count": 200
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": 0.07113428797040666,
-            "min": -0.37446071580052376,
-            "max": 0.30961999893188474,
-            "count": 100
+            "value": -0.116802798701333,
+            "min": -0.31984999863540425,
+            "max": 0.2896556258201599,
+            "count": 200
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": 9.958800315856934,
-            "min": -41.93960016965866,
-            "max": 37.15439987182617,
-            "count": 100
+            "value": -16.70280021429062,
+            "min": -43.49959981441498,
+            "max": 43.73799949884415,
+            "count": 200
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 100
+            "count": 200
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 100
+            "count": 200
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.024346959691805146,
-            "min": 0.020130672054559304,
-            "max": 0.030631732359567346,
-            "count": 96
+            "value": 0.02735576434788527,
+            "min": 0.019240433953867372,
+            "max": 0.03233269830446564,
+            "count": 193
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.024346959691805146,
-            "min": 0.020130672054559304,
-            "max": 0.030631732359567346,
-            "count": 96
+            "value": 0.02735576434788527,
+            "min": 0.019240433953867372,
+            "max": 0.03233269830446564,
+            "count": 193
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.08962117247283459,
-            "min": 0.06291260526825984,
-            "max": 0.1022199623286724,
-            "count": 96
+            "value": 0.08771065895756086,
+            "min": 0.06325821876525879,
+            "max": 0.10387932596107324,
+            "count": 193
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.08962117247283459,
-            "min": 0.06291260526825984,
-            "max": 0.1022199623286724,
-            "count": 96
+            "value": 0.08771065895756086,
+            "min": 0.06325821876525879,
+            "max": 0.10387932596107324,
+            "count": 193
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.09580556737879913,
-            "min": 0.06390505886326234,
-            "max": 0.10687999129295349,
-            "count": 96
+            "value": 0.09183911470075448,
+            "min": 0.06676506791263818,
+            "max": 0.11285836957395076,
+            "count": 193
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.09580556737879913,
-            "min": 0.06390505886326234,
-            "max": 0.10687999129295349,
-            "count": 96
+            "value": 0.09183911470075448,
+            "min": 0.06676506791263818,
+            "max": 0.11285836957395076,
+            "count": 193
         },
         "SoccerTwos.Policy.LearningRate.mean": {
             "value": 0.00010000000000000003,
             "min": 0.00010000000000000003,
             "max": 0.00010000000000000003,
-            "count": 96
+            "count": 193
         },
         "SoccerTwos.Policy.LearningRate.sum": {
             "value": 0.00010000000000000003,
             "min": 0.00010000000000000003,
             "max": 0.00010000000000000003,
-            "count": 96
+            "count": 193
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.30000000000000004,
             "min": 0.30000000000000004,
             "max": 0.30000000000000004,
-            "count": 96
+            "count": 193
         },
         "SoccerTwos.Policy.Epsilon.sum": {
             "value": 0.30000000000000004,
             "min": 0.30000000000000004,
             "max": 0.30000000000000004,
-            "count": 96
+            "count": 193
         },
         "SoccerTwos.Policy.Beta.mean": {
             "value": 0.010000000000000002,
             "min": 0.010000000000000002,
             "max": 0.010000000000000002,
-            "count": 96
+            "count": 193
         },
         "SoccerTwos.Policy.Beta.sum": {
             "value": 0.010000000000000002,
             "min": 0.010000000000000002,
             "max": 0.010000000000000002,
-            "count": 96
+            "count": 193
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1718354770",
+        "start_time_seconds": "1718522799",
         "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": "1718357413"
+        "end_time_seconds": "1718527806"
     },
-    "total": 2643.438411529,
+    "total": 5007.439330968,
     "count": 1,
-    "self": 0.44061282700022275,
+    "self": 0.7543871560001207,
     "children": {
         "run_training.setup": {
-            "total": 0.05524954800000614,
+            "total": 0.05655190099992069,
             "count": 1,
-            "self": 0.05524954800000614
+            "self": 0.05655190099992069
         },
         "TrainerController.start_learning": {
-            "total": 2642.9425491539996,
+            "total": 5006.628391911,
             "count": 1,
-            "self": 1.7481662440723085,
+            "self": 3.198314339836543,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.148299596000129,
-                    "count": 6,
-                    "self": 3.148299596000129
+                    "total": 3.5251714379982104,
+                    "count": 11,
+                    "self": 3.5251714379982104
                 },
                 "TrainerController.advance": {
-                    "total": 2637.7337122209274,
-                    "count": 67963,
-                    "self": 1.899848016994838,
+                    "total": 4999.476015936164,
+                    "count": 137066,
+                    "self": 3.4961768883786135,
                     "children": {
                         "env_step": {
-                            "total": 1835.5979456299804,
-                            "count": 67963,
-                            "self": 1395.1376912010285,
+                            "total": 3411.0316363288134,
+                            "count": 137066,
+                            "self": 2609.0772045809367,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 439.4613840100016,
-                                    "count": 67963,
-                                    "self": 11.93888216498624,
+                                    "total": 800.1073373739822,
+                                    "count": 137066,
+                                    "self": 21.254987563703594,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 427.52250184501537,
-                                            "count": 125514,
-                                            "self": 427.52250184501537
+                                            "total": 778.8523498102786,
+                                            "count": 251158,
+                                            "self": 778.8523498102786
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.9988704189502755,
-                                    "count": 67963,
+                                    "total": 1.8470943738943788,
+                                    "count": 137066,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2638.251060065022,
-                                            "count": 67963,
+                                            "total": 4998.292369874953,
+                                            "count": 137066,
                                             "is_parallel": true,
-                                            "self": 1467.0694028729831,
+                                            "self": 2805.5120150558128,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -265,48 +265,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.007002816000010625,
+                                                            "total": 0.006566367000004902,
                                                             "count": 2,
                                                             "is_parallel": true,
-                                                            "self": 0.0037053229999628456,
+                                                            "self": 0.004183040999919285,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.00329749300004778,
+                                                                    "total": 0.002383326000085617,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00329749300004778
+                                                                    "self": 0.002383326000085617
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.042755231000001004,
+                                                            "total": 0.03895461900003738,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0011683379999567478,
+                                                            "self": 0.001148698999941189,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0008768920000079561,
+                                                                    "total": 0.0008545309999590245,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0008768920000079561
+                                                                    "self": 0.0008545309999590245
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.037155740999992304,
+                                                                    "total": 0.033607563000032314,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.037155740999992304
+                                                                    "self": 0.033607563000032314
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.003554260000043996,
+                                                                    "total": 0.0033438260001048548,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0006907179999871005,
+                                                                    "self": 0.0006034259997704794,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0028635420000568956,
+                                                                            "total": 0.0027404000003343754,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0028635420000568956
+                                                                            "self": 0.0027404000003343754
                                                                         }
                                                                     }
                                                                 }
@@ -315,48 +315,48 @@
                                                     }
                                                 },
                                                 "steps_from_proto": {
-                                                    "total": 0.010347326000214707,
-                                                    "count": 10,
+                                                    "total": 0.021407936998798505,
+                                                    "count": 20,
                                                     "is_parallel": true,
-                                                    "self": 0.0023058779999587387,
+                                                    "self": 0.004499890997408329,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.008041448000255969,
-                                                            "count": 40,
+                                                            "total": 0.016908046001390176,
+                                                            "count": 80,
                                                             "is_parallel": true,
-                                                            "self": 0.008041448000255969
+                                                            "self": 0.016908046001390176
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1171.1713098660387,
-                                                    "count": 67962,
+                                                    "total": 2192.758946882141,
+                                                    "count": 137065,
                                                     "is_parallel": true,
-                                                    "self": 72.15924076098236,
+                                                    "self": 138.32599547621658,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 50.23150113503095,
-                                                            "count": 67962,
+                                                            "total": 91.2733081709871,
+                                                            "count": 137065,
                                                             "is_parallel": true,
-                                                            "self": 50.23150113503095
+                                                            "self": 91.2733081709871
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 815.8509057829692,
-                                                            "count": 67962,
+                                                            "total": 1532.1396728770892,
+                                                            "count": 137065,
                                                             "is_parallel": true,
-                                                            "self": 815.8509057829692
+                                                            "self": 1532.1396728770892
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 232.92966218705607,
-                                                            "count": 135924,
+                                                            "total": 431.019970357848,
+                                                            "count": 274130,
                                                             "is_parallel": true,
-                                                            "self": 39.79592852296594,
+                                                            "self": 72.08200654269149,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 193.13373366409013,
-                                                                    "count": 543696,
+                                                                    "total": 358.93796381515654,
+                                                                    "count": 1096520,
                                                                     "is_parallel": true,
-                                                                    "self": 193.13373366409013
+                                                                    "self": 358.93796381515654
                                                                 }
                                                             }
                                                         }
@@ -369,31 +369,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 800.2359185739523,
-                            "count": 67963,
-                            "self": 13.141391972977772,
+                            "total": 1584.948202718972,
+                            "count": 137066,
+                            "self": 24.71473832306583,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 223.8453884169735,
-                                    "count": 67963,
-                                    "self": 223.12084548197345,
+                                    "total": 438.04711281591324,
+                                    "count": 137066,
+                                    "self": 436.77035079591235,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.724542935000045,
-                                            "count": 2,
-                                            "self": 0.724542935000045
+                                            "total": 1.2767620200008878,
+                                            "count": 4,
+                                            "self": 1.2767620200008878
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 563.249138184001,
-                                    "count": 96,
-                                    "self": 308.2580305080081,
+                                    "total": 1122.186351579993,
+                                    "count": 193,
+                                    "self": 610.287240083011,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 254.9911076759929,
-                                            "count": 5760,
-                                            "self": 254.9911076759929
+                                            "total": 511.89911149698196,
+                                            "count": 11580,
+                                            "self": 511.89911149698196
                                         }
                                     }
                                 }
@@ -402,19 +402,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.0160001693293452e-06,
+                    "total": 1.1520005500642583e-06,
                     "count": 1,
-                    "self": 1.0160001693293452e-06
+                    "self": 1.1520005500642583e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.3123700769997413,
+                    "total": 0.4288890450006875,
                     "count": 1,
-                    "self": 0.004324635999637394,
+                    "self": 0.005406617000517144,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.3080454410001039,
+                            "total": 0.42348242800017033,
                             "count": 1,
-                            "self": 0.3080454410001039
+                            "self": 0.42348242800017033
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,59 +2,59 @@
     "SoccerTwos": {
         "checkpoints": [
             {
-                "steps": 3999748,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3999748.onnx",
+                "steps": 5499958,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-5499958.onnx",
                 "reward": 0.0,
-                "creation_time": 1718282009.9757707,
+                "creation_time": 1718524039.1005392,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-3999748.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-5499958.pt"
                 ]
             },
             {
-                "steps": 4000084,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-4000084.onnx",
+                "steps": 5999962,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-5999962.onnx",
                 "reward": 0.0,
-                "creation_time": 1718282010.2985783,
+                "creation_time": 1718525261.7350626,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-4000084.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-5999962.pt"
                 ]
             },
             {
-                "steps": 4499964,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-4499964.onnx",
+                "steps": 6499901,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-6499901.onnx",
                 "reward": 0.0,
-                "creation_time": 1718356086.3615174,
+                "creation_time": 1718526533.052647,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-4499964.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-6499901.pt"
                 ]
             },
             {
-                "steps": 4999989,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-4999989.onnx",
+                "steps": 6999977,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-6999977.onnx",
                 "reward": 0.0,
-                "creation_time": 1718357412.9373324,
+                "creation_time": 1718527805.757467,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-4999989.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-6999977.pt"
                 ]
             },
             {
-                "steps": 5000036,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-5000036.onnx",
+                "steps": 7000094,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-7000094.onnx",
                 "reward": 0.0,
-                "creation_time": 1718357413.2604034,
+                "creation_time": 1718527806.2096646,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-5000036.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-7000094.pt"
                 ]
             }
         ],
-        "elo": 1480.663296751519,
+        "elo": 1496.2597108583236,
         "final_checkpoint": {
-            "steps": 5000036,
+            "steps": 7000094,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1718357413.2604034,
+            "creation_time": 1718527806.2096646,
             "auxillary_file_paths": [
-                "results/SoccerTwos/SoccerTwos/SoccerTwos-5000036.pt"
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-7000094.pt"
             ]
         }
     },