Update_agent

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b75de45a94542dfd99bfede6e8ad0231c8d1669a997bfd205a83433b17abea1
+oid sha256:68747129609ba655ec3bad6b0988b2779d9ee200f0724cd28928b5910e1b4ddd
 size 886472

SoccerTwos/SoccerTwos-4499846.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d709da0df0d94005b99602df32c7dc9e616c5d0051ae7bde489c86d5f98a32a9
+size 886472

SoccerTwos/SoccerTwos-4499846.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dfb9ab620e9e38d1b61b693c28ed71455eafaf13edf8d80182028fbdf2d802b
+size 10303217

SoccerTwos/SoccerTwos-4763422.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68747129609ba655ec3bad6b0988b2779d9ee200f0724cd28928b5910e1b4ddd
+size 886472

SoccerTwos/SoccerTwos-4763422.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:743527733c484bb1d4d10eadc4a4263960e6d08f3287d950afa2d59096fae28a
+size 10303217

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8fb8435d2a687b94510b1567a2c949e8d2ddcb78fff85972594ce1171383af9
+oid sha256:743527733c484bb1d4d10eadc4a4263960e6d08f3287d950afa2d59096fae28a
 size 10303217

SoccerTwos/events.out.tfevents.1690881736.93ce20cc1c4b.27609.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd54f942d20f01a99ae492c8e37bc169c3e34fe6b3f19e3504b90c00ca2a50d4
+size 525155

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.99, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.95, "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": 4250000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 60000, "team_change": 225000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.25, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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}, "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": "cpu"}, "debug": false}
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.99, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.95, "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": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 60000, "team_change": 225000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.25, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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}, "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": "cpu"}, "debug": false}

configuration.yaml

@@ -37,7 +37,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 4250000
+    max_steps: 5000000
     time_horizon: 1000
     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  0.122 seconds
+- Completed reload, in  0.095 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: 0.942733 ms
+UnloadTime: 1.074169 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
@@ -73,51 +73,12 @@ TOO LONG
 TOO LONG
 TOO LONG
 TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
 Setting up 1 worker threads for Enlighten.
 Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 14350 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 9778 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
@@ -233,19 +194,19 @@ 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]: 14351 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 9779 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]: 14351 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 9779 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 17.6 MB
@@ -277,13 +238,13 @@ 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]: 14350 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 9778 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]: 14351 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 9779 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -295,13 +256,13 @@ 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]: 14351 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 9779 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]: 14350 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 9778 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
@@ -313,13 +274,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 14351 frames
+      Peak usage frame count: [0-1.0 KB]: 9779 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]: 14350 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 9778 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": 2.9653992652893066,
-            "min": 2.928091049194336,
-            "max": 3.089735984802246,
-            "count": 75
+            "value": 2.8876917362213135,
+            "min": 2.8207671642303467,
+            "max": 2.9670047760009766,
+            "count": 51
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 55322.48828125,
-            "min": 30992.189453125,
-            "max": 94720.8671875,
-            "count": 75
+            "value": 61450.08203125,
+            "min": 38542.9609375,
+            "max": 81095.3125,
+            "count": 51
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 258.5263157894737,
-            "min": 126.6923076923077,
-            "max": 539.2222222222222,
-            "count": 75
+            "value": 121.7560975609756,
+            "min": 101.52,
+            "max": 321.0625,
+            "count": 51
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19648.0,
-            "min": 16400.0,
-            "max": 23072.0,
-            "count": 75
+            "value": 19968.0,
+            "min": 16644.0,
+            "max": 22748.0,
+            "count": 51
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1288.917142349652,
-            "min": 1265.364925775114,
-            "max": 1319.9948589635467,
-            "count": 75
+            "value": 1320.239355820863,
+            "min": 1287.7026638994375,
+            "max": 1330.3663219670505,
+            "count": 51
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 46401.01712458747,
-            "min": 17796.887486172378,
-            "max": 99141.74676083495,
-            "count": 75
+            "value": 108259.62717731076,
+            "min": 33879.31186780395,
+            "max": 134954.90925107108,
+            "count": 51
         },
         "SoccerTwos.Step.mean": {
-            "value": 4249607.0,
-            "min": 3509874.0,
-            "max": 4249607.0,
-            "count": 75
+            "value": 4759804.0,
+            "min": 4259832.0,
+            "max": 4759804.0,
+            "count": 51
         },
         "SoccerTwos.Step.sum": {
-            "value": 4249607.0,
-            "min": 3509874.0,
-            "max": 4249607.0,
-            "count": 75
+            "value": 4759804.0,
+            "min": 4259832.0,
+            "max": 4759804.0,
+            "count": 51
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": 0.033912427723407745,
-            "min": -0.02116245962679386,
-            "max": 0.08301462978124619,
-            "count": 75
+            "value": 0.020447492599487305,
+            "min": -0.03045905940234661,
+            "max": 0.06636790931224823,
+            "count": 51
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": 1.322584629058838,
-            "min": -1.5871844291687012,
-            "max": 4.439652919769287,
-            "count": 75
+            "value": 1.6562469005584717,
+            "min": -2.132134199142456,
+            "max": 5.3094329833984375,
+            "count": 51
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.035285141319036484,
-            "min": -0.031118163838982582,
-            "max": 0.0905672013759613,
-            "count": 75
+            "value": 0.017545517534017563,
+            "min": -0.031816624104976654,
+            "max": 0.06460098922252655,
+            "count": 51
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 1.3761205673217773,
-            "min": -2.3338623046875,
-            "max": 5.524599075317383,
-            "count": 75
+            "value": 1.421186923980713,
+            "min": -2.227163791656494,
+            "max": 5.168078899383545,
+            "count": 51
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 75
+            "count": 51
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 75
+            "count": 51
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.03541025595787244,
-            "min": -0.5060222225470675,
-            "max": 0.3610142873866217,
-            "count": 75
+            "value": 0.04949876482104078,
+            "min": -0.44826956417249597,
+            "max": 0.3809419370466663,
+            "count": 51
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -1.3809999823570251,
-            "min": -19.56760013103485,
-            "max": 17.24120005965233,
-            "count": 75
+            "value": 4.009399950504303,
+            "min": -24.692399859428406,
+            "max": 23.684000194072723,
+            "count": 51
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.03541025595787244,
-            "min": -0.5060222225470675,
-            "max": 0.3610142873866217,
-            "count": 75
+            "value": 0.04949876482104078,
+            "min": -0.44826956417249597,
+            "max": 0.3809419370466663,
+            "count": 51
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -1.3809999823570251,
-            "min": -19.56760013103485,
-            "max": 17.24120005965233,
-            "count": 75
+            "value": 4.009399950504303,
+            "min": -24.692399859428406,
+            "max": 23.684000194072723,
+            "count": 51
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 75
+            "count": 51
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 75
+            "count": 51
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.016938292739602425,
-            "min": 0.010926229831723807,
-            "max": 0.02053702191139261,
-            "count": 35
+            "value": 0.01967894861008972,
+            "min": 0.011268266525197154,
+            "max": 0.020230189079787426,
+            "count": 24
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.016938292739602425,
-            "min": 0.010926229831723807,
-            "max": 0.02053702191139261,
-            "count": 35
+            "value": 0.01967894861008972,
+            "min": 0.011268266525197154,
+            "max": 0.020230189079787426,
+            "count": 24
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.026586440950632097,
-            "min": 0.012621084662775199,
-            "max": 0.03861811061700185,
-            "count": 35
+            "value": 0.05312239018579324,
+            "min": 0.020253862130145232,
+            "max": 0.05312239018579324,
+            "count": 24
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.026586440950632097,
-            "min": 0.012621084662775199,
-            "max": 0.03861811061700185,
-            "count": 35
+            "value": 0.05312239018579324,
+            "min": 0.020253862130145232,
+            "max": 0.05312239018579324,
+            "count": 24
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.027341894370814166,
-            "min": 0.012977093706528347,
-            "max": 0.03994991021851699,
-            "count": 35
+            "value": 0.053971994171539944,
+            "min": 0.0205108476181825,
+            "max": 0.053971994171539944,
+            "count": 24
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.027341894370814166,
-            "min": 0.012977093706528347,
-            "max": 0.03994991021851699,
-            "count": 35
+            "value": 0.053971994171539944,
+            "min": 0.0205108476181825,
+            "max": 0.053971994171539944,
+            "count": 24
         },
         "SoccerTwos.Policy.LearningRate.mean": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 35
+            "count": 24
         },
         "SoccerTwos.Policy.LearningRate.sum": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 35
+            "count": 24
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.20000000000000007,
             "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 35
+            "count": 24
         },
         "SoccerTwos.Policy.Epsilon.sum": {
             "value": 0.20000000000000007,
             "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 35
+            "count": 24
         },
         "SoccerTwos.Policy.Beta.mean": {
             "value": 0.005000000000000001,
             "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 35
+            "count": 24
         },
         "SoccerTwos.Policy.Beta.sum": {
             "value": 0.005000000000000001,
             "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 35
+            "count": 24
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1690878657",
+        "start_time_seconds": "1690881735",
         "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume --torch-device=cpu",
         "mlagents_version": "0.31.0.dev0",
@@ -204,59 +204,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1690881716"
+        "end_time_seconds": "1690883827"
     },
-    "total": 3059.7732766870004,
+    "total": 2092.368268608,
     "count": 1,
-    "self": 1.0997174930007532,
+    "self": 0.1979001319996314,
     "children": {
         "run_training.setup": {
-            "total": 0.04625938999970458,
+            "total": 0.07193058199936786,
             "count": 1,
-            "self": 0.04625938999970458
+            "self": 0.07193058199936786
         },
         "TrainerController.start_learning": {
-            "total": 3058.627299804,
+            "total": 2092.098437894001,
             "count": 1,
-            "self": 1.995636533916695,
+            "self": 1.3687143129127435,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 1.7464096760004395,
-                    "count": 5,
-                    "self": 1.7464096760004395
+                    "total": 2.0978165780015843,
+                    "count": 4,
+                    "self": 2.0978165780015843
                 },
                 "TrainerController.advance": {
-                    "total": 3054.504729847082,
-                    "count": 49247,
-                    "self": 2.1494134940912772,
+                    "total": 2088.2893669790856,
+                    "count": 33907,
+                    "self": 1.515300722034226,
                     "children": {
                         "env_step": {
-                            "total": 1728.580282753981,
-                            "count": 49247,
-                            "self": 1451.0359896730588,
+                            "total": 1177.2803954150677,
+                            "count": 33907,
+                            "self": 988.0741699530299,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 276.30703805185794,
-                                    "count": 49247,
-                                    "self": 14.137087277108094,
+                                    "total": 188.3656657649408,
+                                    "count": 33907,
+                                    "self": 9.67237968293557,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 262.16995077474985,
-                                            "count": 95670,
-                                            "self": 262.16995077474985
+                                            "total": 178.69328608200522,
+                                            "count": 65188,
+                                            "self": 178.69328608200522
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 1.237255029064272,
-                                    "count": 49247,
+                                    "total": 0.8405596970969782,
+                                    "count": 33906,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 3040.5957244619613,
-                                            "count": 49247,
+                                            "total": 2080.6260435219747,
+                                            "count": 33906,
                                             "is_parallel": true,
-                                            "self": 1839.4196168309827,
+                                            "self": 1264.0824636251018,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -265,48 +265,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.004600864000167348,
+                                                            "total": 0.005448173998956918,
                                                             "count": 2,
                                                             "is_parallel": true,
-                                                            "self": 0.0013356340009522683,
+                                                            "self": 0.001225335997332877,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.00326522999921508,
+                                                                    "total": 0.004222838001624041,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00326522999921508
+                                                                    "self": 0.004222838001624041
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.05661161500029266,
+                                                            "total": 0.08946812399972259,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0014208450006663043,
+                                                            "self": 0.0013794329979646136,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0015787909997015959,
+                                                                    "total": 0.0010004420000768732,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0015787909997015959
+                                                                    "self": 0.0010004420000768732
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04902488400011862,
+                                                                    "total": 0.08189172700076597,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04902488400011862
+                                                                    "self": 0.08189172700076597
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0045870949998061405,
+                                                                    "total": 0.005196522000915138,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0008254869999291259,
+                                                                    "self": 0.0008197640017897356,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0037616079998770147,
+                                                                            "total": 0.004376757999125402,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0037616079998770147
+                                                                            "self": 0.004376757999125402
                                                                         }
                                                                     }
                                                                 }
@@ -315,48 +315,48 @@
                                                     }
                                                 },
                                                 "steps_from_proto": {
-                                                    "total": 0.012616636001439474,
-                                                    "count": 8,
+                                                    "total": 0.015055878999191918,
+                                                    "count": 6,
                                                     "is_parallel": true,
-                                                    "self": 0.0025250890007555427,
+                                                    "self": 0.004368747001535667,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.010091547000683931,
-                                                            "count": 32,
+                                                            "total": 0.010687131997656252,
+                                                            "count": 24,
                                                             "is_parallel": true,
-                                                            "self": 0.010091547000683931
+                                                            "self": 0.010687131997656252
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1201.163490994977,
-                                                    "count": 49246,
+                                                    "total": 816.5285240178737,
+                                                    "count": 33905,
                                                     "is_parallel": true,
-                                                    "self": 71.97562404471091,
+                                                    "self": 48.9032563548335,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 37.76953575507514,
-                                                            "count": 49246,
+                                                            "total": 26.270664289936576,
+                                                            "count": 33905,
                                                             "is_parallel": true,
-                                                            "self": 37.76953575507514
+                                                            "self": 26.270664289936576
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 862.6202264811259,
-                                                            "count": 49246,
+                                                            "total": 586.0080959899551,
+                                                            "count": 33905,
                                                             "is_parallel": true,
-                                                            "self": 862.6202264811259
+                                                            "self": 586.0080959899551
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 228.79810471406518,
-                                                            "count": 98492,
+                                                            "total": 155.3465073831485,
+                                                            "count": 67810,
                                                             "is_parallel": true,
-                                                            "self": 41.2123752680468,
+                                                            "self": 28.16203075564499,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 187.58572944601838,
-                                                                    "count": 393968,
+                                                                    "total": 127.1844766275035,
+                                                                    "count": 271240,
                                                                     "is_parallel": true,
-                                                                    "self": 187.58572944601838
+                                                                    "self": 127.1844766275035
                                                                 }
                                                             }
                                                         }
@@ -369,31 +369,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 1323.77503359901,
-                            "count": 49247,
-                            "self": 16.65251782910582,
+                            "total": 909.4936708419837,
+                            "count": 33906,
+                            "self": 10.893767241996102,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 211.0241680079057,
-                                    "count": 49247,
-                                    "self": 210.79081530890608,
+                                    "total": 150.23692006298825,
+                                    "count": 33906,
+                                    "self": 150.00083145698864,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.2333526989996244,
+                                            "total": 0.2360886059996119,
                                             "count": 1,
-                                            "self": 0.2333526989996244
+                                            "self": 0.2360886059996119
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 1096.0983477619984,
-                                    "count": 35,
-                                    "self": 203.32014813700744,
+                                    "total": 748.3629835369993,
+                                    "count": 24,
+                                    "self": 139.45484663401294,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 892.778199624991,
-                                            "count": 1050,
-                                            "self": 892.778199624991
+                                            "total": 608.9081369029864,
+                                            "count": 720,
+                                            "self": 608.9081369029864
                                         }
                                     }
                                 }
@@ -402,19 +402,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 2.0180004867142998e-06,
+                    "total": 1.8930004443973303e-06,
                     "count": 1,
-                    "self": 2.0180004867142998e-06
+                    "self": 1.8930004443973303e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.38052172900006553,
+                    "total": 0.34253813100076513,
                     "count": 1,
-                    "self": 0.0025554750000083004,
+                    "self": 0.003085514001213596,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.37796625400005723,
+                            "total": 0.33945261699955154,
                             "count": 1,
-                            "self": 0.37796625400005723
+                            "self": 0.33945261699955154
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,24 +1,6 @@
 {
     "SoccerTwos": {
         "checkpoints": [
-            {
-                "steps": 3499730,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3499730.onnx",
-                "reward": 0.0,
-                "creation_time": 1690878606.362709,
-                "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-3499730.pt"
-                ]
-            },
-            {
-                "steps": 3501730,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3501730.onnx",
-                "reward": 0.0,
-                "creation_time": 1690878606.9998047,
-                "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-3501730.pt"
-                ]
-            },
             {
                 "steps": 3501730,
                 "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3501730.onnx",
@@ -45,16 +27,34 @@
                 "auxillary_file_paths": [
                     "results/SoccerTwos/SoccerTwos/SoccerTwos-4250002.pt"
                 ]
+            },
+            {
+                "steps": 4499846,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-4499846.onnx",
+                "reward": 0.0,
+                "creation_time": 1690882739.565591,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-4499846.pt"
+                ]
+            },
+            {
+                "steps": 4763422,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-4763422.onnx",
+                "reward": 0.0,
+                "creation_time": 1690883827.2801886,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-4763422.pt"
+                ]
             }
         ],
-        "elo": 1289.5658096727527,
+        "elo": 1323.2821948929457,
         "final_checkpoint": {
-            "steps": 4250002,
+            "steps": 4763422,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1690881715.7374275,
+            "creation_time": 1690883827.2801886,
             "auxillary_file_paths": [
-                "results/SoccerTwos/SoccerTwos/SoccerTwos-4250002.pt"
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-4763422.pt"
             ]
         }
     },