Update_agent

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fcdaf66071f617228c2ecef7d04944a0ae2741f5974f5f81ba51b51b7730543
+oid sha256:fae1a0fe59597b0c6945fa72e27198ffac28020e3dc49e0ecbcad8342ec4dc2e
 size 886472

SoccerTwos/SoccerTwos-6999984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fae1a0fe59597b0c6945fa72e27198ffac28020e3dc49e0ecbcad8342ec4dc2e
+size 886472

SoccerTwos/SoccerTwos-6999984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cef90d30b6c661aaa0851a597d13c885f15eb9949d33413ff14d699dad46786
+size 10303217

SoccerTwos/SoccerTwos-7000018.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fae1a0fe59597b0c6945fa72e27198ffac28020e3dc49e0ecbcad8342ec4dc2e
+size 886472

SoccerTwos/SoccerTwos-7000018.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91d03981cc1e27ab47f3a2f50d8d6b1e5f11ff96db9082417885e6f29073cb1c
+size 10303217

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:182a0da6adb3fe4453923f517828c37f68dcc553dc0f4ed01c218e4f1e453e18
+oid sha256:91d03981cc1e27ab47f3a2f50d8d6b1e5f11ff96db9082417885e6f29073cb1c
 size 10303217

SoccerTwos/events.out.tfevents.1690891422.93ce20cc1c4b.66636.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad06dd27ecd00e303d977a14e54b2ec7fb805a8e05e0680a027864d788c53634
+size 515045

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": 6500000, "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": 7000000, "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: 6500000
+    max_steps: 7000000
     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  0.096 seconds
+- Completed reload, in  0.093 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: 0.884204 ms
+UnloadTime: 0.864206 ms
 Registered Communicator in Agent.
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
@@ -65,7 +65,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 14134 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 9424 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.1 MB
@@ -181,23 +181,23 @@ 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: [16.0 MB-32.0 MB]: 14135 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 9425 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 20.6 MB
-      Peak Large allocation bytes 16.0 MB
+      Peak Allocated memory 4.6 MB
+      Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 14135 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 9425 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 1.6 MB
-      Peak Large allocation bytes 0 B
+      Peak Allocated memory 17.6 MB
+      Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
   Used Block Count 1
@@ -225,13 +225,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 14134 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 9424 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]: 14135 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 9425 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -243,13 +243,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 14135 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 9425 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]: 14134 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 9424 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.5 MB
@@ -261,13 +261,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 14135 frames
+      Peak usage frame count: [0-1.0 KB]: 9425 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]: 14134 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 9424 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": 2.4647605419158936,
-            "min": 2.4436533451080322,
-            "max": 2.6065003871917725,
-            "count": 75
+            "value": 2.3667643070220947,
+            "min": 2.33071231842041,
+            "max": 2.5206995010375977,
+            "count": 50
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 49452.95703125,
-            "min": 42656.33203125,
-            "max": 57644.62109375,
-            "count": 75
+            "value": 47562.49609375,
+            "min": 44078.4296875,
+            "max": 55899.03125,
+            "count": 50
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 49.34020618556701,
-            "min": 43.92727272727273,
-            "max": 86.55,
-            "count": 75
+            "value": 48.88,
+            "min": 43.7304347826087,
+            "max": 61.69620253164557,
+            "count": 50
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19144.0,
-            "min": 18468.0,
-            "max": 20828.0,
-            "count": 75
+            "value": 19552.0,
+            "min": 18684.0,
+            "max": 20208.0,
+            "count": 50
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1446.3990784066912,
-            "min": 1407.1527249916471,
-            "max": 1466.4331764449346,
-            "count": 75
+            "value": 1470.7483954716015,
+            "min": 1435.3163092525817,
+            "max": 1490.4149327494056,
+            "count": 50
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 280601.4212108981,
-            "min": 170986.03853388596,
-            "max": 318622.23212539963,
-            "count": 75
+            "value": 294149.6790943203,
+            "min": 230435.66739658496,
+            "max": 335717.66091586347,
+            "count": 50
         },
         "SoccerTwos.Step.mean": {
-            "value": 6499934.0,
-            "min": 5759934.0,
-            "max": 6499934.0,
-            "count": 75
+            "value": 6999984.0,
+            "min": 6509978.0,
+            "max": 6999984.0,
+            "count": 50
         },
         "SoccerTwos.Step.sum": {
-            "value": 6499934.0,
-            "min": 5759934.0,
-            "max": 6499934.0,
-            "count": 75
+            "value": 6999984.0,
+            "min": 6509978.0,
+            "max": 6999984.0,
+            "count": 50
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": 0.06069766357541084,
-            "min": -0.028229886665940285,
-            "max": 0.08104612678289413,
-            "count": 75
+            "value": 0.07726456969976425,
+            "min": -0.030845150351524353,
+            "max": 0.07726456969976425,
+            "count": 50
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": 11.836044311523438,
-            "min": -4.190831184387207,
-            "max": 13.453786849975586,
-            "count": 75
+            "value": 15.452914237976074,
+            "min": -6.045649528503418,
+            "max": 15.91751480102539,
+            "count": 50
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.05713004246354103,
-            "min": -0.03292163461446762,
-            "max": 0.07865509390830994,
-            "count": 75
+            "value": 0.07707680016756058,
+            "min": -0.0268353670835495,
+            "max": 0.07984796911478043,
+            "count": 50
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 11.140357971191406,
-            "min": -4.719839096069336,
-            "max": 13.713396072387695,
-            "count": 75
+            "value": 15.415359497070312,
+            "min": -5.259731769561768,
+            "max": 16.76807403564453,
+            "count": 50
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 75
+            "count": 50
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 75
+            "count": 50
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": 0.15984615301474547,
-            "min": -0.2143614891893375,
-            "max": 0.23290133158365886,
-            "count": 75
+            "value": 0.18601200073957444,
+            "min": -0.22530110065753645,
+            "max": 0.3014857155936105,
+            "count": 50
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": 31.169999837875366,
-            "min": -34.51219975948334,
-            "max": 34.93519973754883,
-            "count": 75
+            "value": 37.20240014791489,
+            "min": -41.00480031967163,
+            "max": 63.3120002746582,
+            "count": 50
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": 0.15984615301474547,
-            "min": -0.2143614891893375,
-            "max": 0.23290133158365886,
-            "count": 75
+            "value": 0.18601200073957444,
+            "min": -0.22530110065753645,
+            "max": 0.3014857155936105,
+            "count": 50
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": 31.169999837875366,
-            "min": -34.51219975948334,
-            "max": 34.93519973754883,
-            "count": 75
+            "value": 37.20240014791489,
+            "min": -41.00480031967163,
+            "max": 63.3120002746582,
+            "count": 50
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 75
+            "count": 50
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 75
+            "count": 50
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.014913784746204329,
-            "min": 0.012705877462091545,
-            "max": 0.02106438890332356,
-            "count": 36
+            "value": 0.01691505271786203,
+            "min": 0.012469863990554586,
+            "max": 0.02095626645217029,
+            "count": 24
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.014913784746204329,
-            "min": 0.012705877462091545,
-            "max": 0.02106438890332356,
-            "count": 36
+            "value": 0.01691505271786203,
+            "min": 0.012469863990554586,
+            "max": 0.02095626645217029,
+            "count": 24
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.08063839798172315,
-            "min": 0.06412938882907232,
-            "max": 0.08411871741215388,
-            "count": 36
+            "value": 0.07490279500683149,
+            "min": 0.06604709873596827,
+            "max": 0.08390739584962527,
+            "count": 24
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.08063839798172315,
-            "min": 0.06412938882907232,
-            "max": 0.08411871741215388,
-            "count": 36
+            "value": 0.07490279500683149,
+            "min": 0.06604709873596827,
+            "max": 0.08390739584962527,
+            "count": 24
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.08215803081790606,
-            "min": 0.06557651174565156,
-            "max": 0.08553109541535378,
-            "count": 36
+            "value": 0.07590456182758014,
+            "min": 0.06684525907039643,
+            "max": 0.08611040810743968,
+            "count": 24
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.08215803081790606,
-            "min": 0.06557651174565156,
-            "max": 0.08553109541535378,
-            "count": 36
+            "value": 0.07590456182758014,
+            "min": 0.06684525907039643,
+            "max": 0.08611040810743968,
+            "count": 24
         },
         "SoccerTwos.Policy.LearningRate.mean": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 36
+            "count": 24
         },
         "SoccerTwos.Policy.LearningRate.sum": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 36
+            "count": 24
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.20000000000000007,
             "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 36
+            "count": 24
         },
         "SoccerTwos.Policy.Epsilon.sum": {
             "value": 0.20000000000000007,
             "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 36
+            "count": 24
         },
         "SoccerTwos.Policy.Beta.mean": {
             "value": 0.005000000000000001,
             "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 36
+            "count": 24
         },
         "SoccerTwos.Policy.Beta.sum": {
             "value": 0.005000000000000001,
             "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 36
+            "count": 24
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1690888271",
+        "start_time_seconds": "1690891421",
         "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": "1690891406"
+        "end_time_seconds": "1690893542"
     },
-    "total": 3134.5549977269984,
+    "total": 2121.240111834999,
     "count": 1,
-    "self": 0.5773417409982358,
+    "self": 0.5420148220000556,
     "children": {
         "run_training.setup": {
-            "total": 0.041487718999633216,
+            "total": 0.04162588399776723,
             "count": 1,
-            "self": 0.041487718999633216
+            "self": 0.04162588399776723
         },
         "TrainerController.start_learning": {
-            "total": 3133.9361682670005,
+            "total": 2120.656471129001,
             "count": 1,
-            "self": 2.2835163210475002,
+            "self": 1.5054543152655242,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 1.2968337049987895,
-                    "count": 5,
-                    "self": 1.2968337049987895
+                    "total": 1.4437276519965963,
+                    "count": 4,
+                    "self": 1.4437276519965963
                 },
                 "TrainerController.advance": {
-                    "total": 3130.138600297956,
-                    "count": 52092,
-                    "self": 2.239194006268008,
+                    "total": 2117.4951610467397,
+                    "count": 35069,
+                    "self": 1.5695238139524008,
                     "children": {
                         "env_step": {
-                            "total": 1712.5569826390547,
-                            "count": 52092,
-                            "self": 1448.387999565768,
+                            "total": 1155.004338777053,
+                            "count": 35069,
+                            "self": 975.2380251731483,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 262.8882053682264,
-                                    "count": 52092,
-                                    "self": 12.37939927491243,
+                                    "total": 178.8851889927828,
+                                    "count": 35069,
+                                    "self": 8.254970399870217,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 250.50880609331398,
-                                            "count": 94230,
-                                            "self": 250.50880609331398
+                                            "total": 170.63021859291257,
+                                            "count": 62828,
+                                            "self": 170.63021859291257
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 1.2807777050602454,
-                                    "count": 52092,
+                                    "total": 0.881124611121777,
+                                    "count": 35069,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 3117.428293702631,
-                                            "count": 52092,
+                                            "total": 2109.615471201516,
+                                            "count": 35069,
                                             "is_parallel": true,
-                                            "self": 1911.5819695236896,
+                                            "self": 1298.5123828862634,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -265,48 +265,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.003298657000414096,
+                                                            "total": 0.005451203000120586,
                                                             "count": 2,
                                                             "is_parallel": true,
-                                                            "self": 0.0008504910019837553,
+                                                            "self": 0.0011757169922930188,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0024481659984303406,
+                                                                    "total": 0.004275486007827567,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0024481659984303406
+                                                                    "self": 0.004275486007827567
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.046987857998828986,
+                                                            "total": 0.07496027600063826,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.001370382000459358,
+                                                            "self": 0.0014275090034061577,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0010125909993803361,
+                                                                    "total": 0.0007755869992251974,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0010125909993803361
+                                                                    "self": 0.0007755869992251974
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.040281173000039416,
+                                                                    "total": 0.06163016799837351,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.040281173000039416
+                                                                    "self": 0.06163016799837351
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.004323711998949875,
+                                                                    "total": 0.011127011999633396,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0007712519964115927,
+                                                                    "self": 0.0008880850000423379,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0035524600025382824,
+                                                                            "total": 0.010238926999591058,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0035524600025382824
+                                                                            "self": 0.010238926999591058
                                                                         }
                                                                     }
                                                                 }
@@ -315,48 +315,48 @@
                                                     }
                                                 },
                                                 "steps_from_proto": {
-                                                    "total": 0.011108942999271676,
-                                                    "count": 8,
+                                                    "total": 0.007095673998264829,
+                                                    "count": 6,
                                                     "is_parallel": true,
-                                                    "self": 0.0020862129968008958,
+                                                    "self": 0.0014340400011860766,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.00902273000247078,
-                                                            "count": 32,
+                                                            "total": 0.005661633997078752,
+                                                            "count": 24,
                                                             "is_parallel": true,
-                                                            "self": 0.00902273000247078
+                                                            "self": 0.005661633997078752
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1205.835215235942,
-                                                    "count": 52091,
+                                                    "total": 811.0959926412543,
+                                                    "count": 35068,
                                                     "is_parallel": true,
-                                                    "self": 71.90485385938155,
+                                                    "self": 48.543254373689706,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 38.48136216392413,
-                                                            "count": 52091,
+                                                            "total": 25.37648238968177,
+                                                            "count": 35068,
                                                             "is_parallel": true,
-                                                            "self": 38.48136216392413
+                                                            "self": 25.37648238968177
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 868.8257394927841,
-                                                            "count": 52091,
+                                                            "total": 584.6229807467062,
+                                                            "count": 35068,
                                                             "is_parallel": true,
-                                                            "self": 868.8257394927841
+                                                            "self": 584.6229807467062
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 226.62325971985229,
-                                                            "count": 104182,
+                                                            "total": 152.55327513117663,
+                                                            "count": 70136,
                                                             "is_parallel": true,
-                                                            "self": 41.60843442960868,
+                                                            "self": 28.184793114080094,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 185.0148252902436,
-                                                                    "count": 416728,
+                                                                    "total": 124.36848201709654,
+                                                                    "count": 280544,
                                                                     "is_parallel": true,
-                                                                    "self": 185.0148252902436
+                                                                    "self": 124.36848201709654
                                                                 }
                                                             }
                                                         }
@@ -369,31 +369,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 1415.3424236526334,
-                            "count": 52092,
-                            "self": 15.513245858084701,
+                            "total": 960.9212984557344,
+                            "count": 35069,
+                            "self": 9.931847368385206,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 282.79064784255206,
-                                    "count": 52092,
-                                    "self": 282.21467366855177,
+                                    "total": 195.88171612734732,
+                                    "count": 35069,
+                                    "self": 195.66547433134838,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.5759741740002937,
-                                            "count": 2,
-                                            "self": 0.5759741740002937
+                                            "total": 0.21624179599893978,
+                                            "count": 1,
+                                            "self": 0.21624179599893978
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 1117.0385299519967,
-                                    "count": 36,
-                                    "self": 198.22306532695438,
+                                    "total": 755.1077349600018,
+                                    "count": 24,
+                                    "self": 137.47176963701713,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 918.8154646250423,
-                                            "count": 1080,
-                                            "self": 918.8154646250423
+                                            "total": 617.6359653229847,
+                                            "count": 720,
+                                            "self": 617.6359653229847
                                         }
                                     }
                                 }
@@ -402,19 +402,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.1209995136596262e-06,
+                    "total": 9.499999578110874e-07,
                     "count": 1,
-                    "self": 1.1209995136596262e-06
+                    "self": 9.499999578110874e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.2172168219985906,
+                    "total": 0.21212716499940143,
                     "count": 1,
-                    "self": 0.0020243499966454692,
+                    "self": 0.0018193489995610435,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.21519247200194513,
+                            "total": 0.2103078159998404,
                             "count": 1,
-                            "self": 0.21519247200194513
+                            "self": 0.2103078159998404
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,24 +1,6 @@
 {
     "SoccerTwos": {
         "checkpoints": [
-            {
-                "steps": 5499812,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-5499812.onnx",
-                "reward": 0.0,
-                "creation_time": 1690886924.3524578,
-                "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-5499812.pt"
-                ]
-            },
-            {
-                "steps": 5750116,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-5750116.onnx",
-                "reward": 0.0,
-                "creation_time": 1690887962.8115568,
-                "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-5750116.pt"
-                ]
-            },
             {
                 "steps": 5999846,
                 "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-5999846.onnx",
@@ -45,16 +27,34 @@
                 "auxillary_file_paths": [
                     "results/SoccerTwos/SoccerTwos/SoccerTwos-6500056.pt"
                 ]
+            },
+            {
+                "steps": 6999984,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-6999984.onnx",
+                "reward": 0.0,
+                "creation_time": 1690893541.6311257,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-6999984.pt"
+                ]
+            },
+            {
+                "steps": 7000018,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-7000018.onnx",
+                "reward": 0.0,
+                "creation_time": 1690893541.8556185,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-7000018.pt"
+                ]
             }
         ],
-        "elo": 1450.908069690864,
+        "elo": 1477.9105270069736,
         "final_checkpoint": {
-            "steps": 6500056,
+            "steps": 7000018,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1690891405.8324199,
+            "creation_time": 1690893541.8556185,
             "auxillary_file_paths": [
-                "results/SoccerTwos/SoccerTwos/SoccerTwos-6500056.pt"
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-7000018.pt"
             ]
         }
     },