Second Push

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa1a7be1bfe2e22e549f7cec25093c3ac3431cc608cdc27be25c993d93c647cf
+oid sha256:f9cfd995f111c1d8f3a5f1b06cf3069f513b369f8c5f7b8dd9181f35b76af803
 size 1768746

SoccerTwos/SoccerTwos-75000024.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fa1a7be1bfe2e22e549f7cec25093c3ac3431cc608cdc27be25c993d93c647cf
-size 1768746

SoccerTwos/SoccerTwos-75000024.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fa2ba7e14df6646e684119b8a16aa512052f0c54aeea6c97e9a177c72d487fa2
-size 28430025

SoccerTwos/{SoccerTwos-73499874.onnx → SoccerTwos-83499918.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd7ae60e961a26a7328ee4895c5d6e1846266dc0fa4b49403beb9d47f3f27fb4
+oid sha256:e9b24919752740f5c6c2c5dde64ee0b2159e4cb154689d23ced84fabf2f0aac7
 size 1768746

SoccerTwos/{SoccerTwos-74499953.pt → SoccerTwos-83499918.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80a15018739e865cd1a9c1ecf3de69abedd169bd491dec3983ccfad99e8ebd09
+oid sha256:a861ea5887433256562bc6adf0aa74a3e7d61ba9112d44ed4c39a58ac9523852
 size 28430025

SoccerTwos/{SoccerTwos-74499953.onnx → SoccerTwos-83999982.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e2dc61645cd887c77f4281ceb37aa58c816b7eb86a7e0422b5111849d7065bf
+oid sha256:bc5af14cb4de5155b70de0321522518b5e021b2c6b45d1b21fe41b922962375b
 size 1768746

SoccerTwos/{SoccerTwos-73499874.pt → SoccerTwos-83999982.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bc3bea067f6496901e1cab595ebe85674233ec8518aabbca3446c6863a960e9
+oid sha256:c2060a2db25a78ec0055b9a8f1f770deaaed3b26bf83d147e07e23fe01880c3b
 size 28430025

SoccerTwos/{SoccerTwos-73999928.onnx → SoccerTwos-84499946.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85b4978c38a5177a9cb92e24ec9559daf341a49b3e180fb780048f097d00ed3a
+oid sha256:2f31b9f0ff95b572686daedb87de010c626b67489454c855e7d930acdafa5e20
 size 1768746

SoccerTwos/{SoccerTwos-74999941.pt → SoccerTwos-84499946.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917ed49c181e7bf9f02e7d2ffe85e76c86a269cc1d26d41ccfb18e4e2468fa07
+oid sha256:f7e7bdc9416e582d9761cd285dc200095e214b8a1679c50a8d2f6e2c72d7efa6
 size 28430025

SoccerTwos/{SoccerTwos-74999941.onnx → SoccerTwos-84999955.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa1a7be1bfe2e22e549f7cec25093c3ac3431cc608cdc27be25c993d93c647cf
+oid sha256:f9cfd995f111c1d8f3a5f1b06cf3069f513b369f8c5f7b8dd9181f35b76af803
 size 1768746

SoccerTwos/{SoccerTwos-73999928.pt → SoccerTwos-84999955.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1edfd8edd0836689408996579d74aa6f92d814d490ca171f9afb2c0e21d563b0
+oid sha256:8cad60903bcb51ead4b3558b912e82fc5ace4df68a8f8ee0cb1b9187dd931ddb
 size 28430025

SoccerTwos/SoccerTwos-85000026.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9cfd995f111c1d8f3a5f1b06cf3069f513b369f8c5f7b8dd9181f35b76af803
+size 1768746

SoccerTwos/SoccerTwos-85000026.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a0385dc69ff29e8e67f6c260a1c9bdcb8f210f42e809cee6594a500a6f4f2b4
+size 28430025

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99a30e77f85fbde3d73d3f396c4c8742bca176558b79980b82e619cc55a962fe
+oid sha256:c3bd217aa4e8ac4a61bd9ffa815ff00f1dc5369d0cb9f47b3634d67c8da3f4e6
 size 28428927

SoccerTwos/events.out.tfevents.1681230639.TRI-LN-LAP31.29752.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efe2b848e93bfb536ec14fb57db277e2567cf6fafe5e7ca9d53ec54b47d3392f
+size 10279052

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": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "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": 75000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 75000, "team_change": 450000, "swap_steps": 10000, "window": 15, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.exe", "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": false, "force": true, "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": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "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": 85000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 75000, "team_change": 450000, "swap_steps": 10000, "window": 15, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.exe", "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": null}, "debug": false}

configuration.yaml

@@ -37,7 +37,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 75000000
+    max_steps: 85000000
     time_horizon: 1000
     summary_freq: 10000
     threaded: false
@@ -72,8 +72,8 @@ checkpoint_settings:
   run_id: SoccerTwos
   initialize_from: null
   load_model: false
-  resume: false
-  force: true
+  resume: true
+  force: false
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -12,7 +12,7 @@ FMOD failed to get driver capabilities ... : "Error initializing output device.
 FMOD failed to get driver capabilities ... : "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.111 seconds
+- Completed reload, in  1.636 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 Microsoft Media Foundation video decoding to texture disabled: graphics device is Null, only Direct3D 11 and Direct3D 12 (only on desktop) are supported for hardware-accelerated video decoding.
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -38,281 +38,15 @@ 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: 0.595400 ms
+UnloadTime: 0.608600 ms
 Registered Communicator in Agent.
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
-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
-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
-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
-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
-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
-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
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
 Setting up 8 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]: 1409009 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 187869 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -325,7 +59,7 @@ Memory Statistics:
     [ALLOC_TEMP_Loading.PreloadManager]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 68.0 KB
+      Peak Allocated Bytes 67.2 KB
       Overflow Count 4
     [ALLOC_TEMP_Background Job.Worker 8]
       Initial Block Size 32.0 KB
@@ -498,19 +232,19 @@ Memory Statistics:
       Peak Allocated Bytes 54 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 5
+  Peak main deferred allocation count 3
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 1409010 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 187870 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 5.0 MB
+      Peak Allocated memory 5.1 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 1409010 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 187870 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 17.3 MB
@@ -542,13 +276,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 1409009 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 187869 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]: 1409010 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 187870 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.6 KB
@@ -560,16 +294,16 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 1409010 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 187870 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]: 1409009 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 187869 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
-      Peak Allocated memory 3.2 MB
+      Peak Allocated memory 2.2 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
@@ -578,13 +312,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 1409010 frames
+      Peak usage frame count: [0-1.0 KB]: 187870 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]: 1409009 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 187869 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

@@ -2,305 +2,305 @@
     "name": "root",
     "gauges": {
         "SoccerTwos.Policy.Entropy.mean": {
-            "value": 1.382652759552002,
-            "min": 1.2902696132659912,
-            "max": 3.2957499027252197,
-            "count": 7500
+            "value": 1.2650021314620972,
+            "min": 1.2380719184875488,
+            "max": 1.468640923500061,
+            "count": 1000
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 26502.6875,
-            "min": 21425.6953125,
-            "max": 112003.6953125,
-            "count": 7500
+            "value": 23761.80078125,
+            "min": 21988.466796875,
+            "max": 32897.56640625,
+            "count": 1000
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 76.09375,
-            "min": 41.07692307692308,
-            "max": 999.0,
-            "count": 7500
+            "value": 67.27397260273973,
+            "min": 51.583333333333336,
+            "max": 116.33333333333333,
+            "count": 1000
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19480.0,
-            "min": 13244.0,
-            "max": 29836.0,
-            "count": 7500
+            "value": 19644.0,
+            "min": 18228.0,
+            "max": 21312.0,
+            "count": 1000
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1992.749268818398,
-            "min": 1200.1761971761618,
-            "max": 2024.858056166232,
-            "count": 7495
+            "value": 2004.5787994439306,
+            "min": 1954.8947872617402,
+            "max": 2041.764258181336,
+            "count": 1000
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 255071.90640875493,
-            "min": 2400.3523943523237,
-            "max": 451496.74931455427,
-            "count": 7495
+            "value": 292668.50471881387,
+            "min": 169423.43903436014,
+            "max": 383670.03688610066,
+            "count": 1000
         },
         "SoccerTwos.Step.mean": {
-            "value": 74999941.0,
-            "min": 9934.0,
-            "max": 74999941.0,
-            "count": 7500
+            "value": 84999955.0,
+            "min": 75009944.0,
+            "max": 84999955.0,
+            "count": 1000
         },
         "SoccerTwos.Step.sum": {
-            "value": 74999941.0,
-            "min": 9934.0,
-            "max": 74999941.0,
-            "count": 7500
+            "value": 84999955.0,
+            "min": 75009944.0,
+            "max": 84999955.0,
+            "count": 1000
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": 0.017558835446834564,
-            "min": -0.15992090106010437,
-            "max": 0.32234451174736023,
-            "count": 7500
+            "value": -0.03205849230289459,
+            "min": -0.11903506517410278,
+            "max": 0.059358175843954086,
+            "count": 1000
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": 2.265089750289917,
-            "min": -25.747264862060547,
-            "max": 55.43302917480469,
-            "count": 7500
+            "value": -4.680540084838867,
+            "min": -16.39316749572754,
+            "max": 9.257532119750977,
+            "count": 1000
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.016945861279964447,
-            "min": -0.16041989624500275,
-            "max": 0.321755588054657,
-            "count": 7500
+            "value": -0.033613935112953186,
+            "min": -0.1195150688290596,
+            "max": 0.05932600796222687,
+            "count": 1000
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2.186016082763672,
-            "min": -25.82760238647461,
-            "max": 54.83216857910156,
-            "count": 7500
+            "value": -4.907634735107422,
+            "min": -16.774024963378906,
+            "max": 9.482162475585938,
+            "count": 1000
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 7500
+            "count": 1000
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 7500
+            "count": 1000
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": 0.13035969031873598,
-            "min": -0.5036316535455717,
-            "max": 0.7454326566384764,
-            "count": 7500
+            "value": -0.07270958856360553,
+            "min": -0.43179082651750755,
+            "max": 0.3916580609736904,
+            "count": 1000
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": 16.816400051116943,
-            "min": -83.653599858284,
-            "max": 106.25999999046326,
-            "count": 7500
+            "value": -10.615599930286407,
+            "min": -59.70240008831024,
+            "max": 52.31599986553192,
+            "count": 1000
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": 0.13035969031873598,
-            "min": -0.5036316535455717,
-            "max": 0.7454326566384764,
-            "count": 7500
+            "value": -0.07270958856360553,
+            "min": -0.43179082651750755,
+            "max": 0.3916580609736904,
+            "count": 1000
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": 16.816400051116943,
-            "min": -83.653599858284,
-            "max": 106.25999999046326,
-            "count": 7500
+            "value": -10.615599930286407,
+            "min": -59.70240008831024,
+            "max": 52.31599986553192,
+            "count": 1000
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 7500
+            "count": 1000
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 7500
+            "count": 1000
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.012527202733326703,
-            "min": 0.00982293396082241,
-            "max": 0.02636458116273085,
-            "count": 3639
+            "value": 0.019802655400902345,
+            "min": 0.011881238495455667,
+            "max": 0.027653722364145022,
+            "count": 485
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.012527202733326703,
-            "min": 0.00982293396082241,
-            "max": 0.02636458116273085,
-            "count": 3639
+            "value": 0.019802655400902345,
+            "min": 0.011881238495455667,
+            "max": 0.027653722364145022,
+            "count": 485
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.09411200359463692,
-            "min": 4.6444494182651395e-05,
-            "max": 0.12619234298666318,
-            "count": 3639
+            "value": 0.09014766265948614,
+            "min": 0.06759478511909643,
+            "max": 0.11066784386833509,
+            "count": 485
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.09411200359463692,
-            "min": 4.6444494182651395e-05,
-            "max": 0.12619234298666318,
-            "count": 3639
+            "value": 0.09014766265948614,
+            "min": 0.06759478511909643,
+            "max": 0.11066784386833509,
+            "count": 485
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.0951201801498731,
-            "min": 4.2040371590701396e-05,
-            "max": 0.12739595472812654,
-            "count": 3639
+            "value": 0.09081148828069369,
+            "min": 0.06813100427389145,
+            "max": 0.1114325650036335,
+            "count": 485
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.0951201801498731,
-            "min": 4.2040371590701396e-05,
-            "max": 0.12739595472812654,
-            "count": 3639
+            "value": 0.09081148828069369,
+            "min": 0.06813100427389145,
+            "max": 0.1114325650036335,
+            "count": 485
         },
         "SoccerTwos.Policy.LearningRate.mean": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 3639
+            "count": 485
         },
         "SoccerTwos.Policy.LearningRate.sum": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 3639
+            "count": 485
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.20000000000000007,
-            "min": 0.2,
+            "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 3639
+            "count": 485
         },
         "SoccerTwos.Policy.Epsilon.sum": {
             "value": 0.20000000000000007,
-            "min": 0.2,
+            "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 3639
+            "count": 485
         },
         "SoccerTwos.Policy.Beta.mean": {
             "value": 0.005000000000000001,
-            "min": 0.005,
+            "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 3639
+            "count": 485
         },
         "SoccerTwos.Policy.Beta.sum": {
             "value": 0.005000000000000001,
-            "min": 0.005,
+            "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 3639
+            "count": 485
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1680888797",
+        "start_time_seconds": "1681230634",
         "python_version": "3.9.16 (main, Mar  8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]",
-        "command_line_arguments": "C:\\Users\\JJarvis-ADM\\.conda\\envs\\rl2\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force",
+        "command_line_arguments": "C:\\Users\\JJarvis-ADM\\.conda\\envs\\rl2\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume",
         "mlagents_version": "0.31.0.dev0",
         "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.0.0+cpu",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1681229164"
+        "end_time_seconds": "1681467910"
     },
-    "total": 340364.9419576,
+    "total": 237278.1721994,
     "count": 1,
-    "self": 0.5030156999710016,
+    "self": 0.49782279998180456,
     "children": {
         "run_training.setup": {
-            "total": 0.09161920000000023,
+            "total": 0.11812080000000158,
             "count": 1,
-            "self": 0.09161920000000023
+            "self": 0.11812080000000158
         },
         "TrainerController.start_learning": {
-            "total": 340364.3473227,
+            "total": 237277.5562558,
             "count": 1,
-            "self": 95.8923158008256,
+            "self": 12.676609797141282,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 5.439333900002533,
-                    "count": 167,
-                    "self": 5.439333900002533
+                    "total": 5.2566997000159486,
+                    "count": 24,
+                    "self": 5.2566997000159486
                 },
                 "TrainerController.advance": {
-                    "total": 340262.8528570992,
-                    "count": 5144774,
-                    "self": 95.78704869915964,
+                    "total": 237259.45996180284,
+                    "count": 680892,
+                    "self": 13.211910992307821,
                     "children": {
                         "env_step": {
-                            "total": 85873.25582839223,
-                            "count": 5144774,
-                            "self": 68785.62908125832,
+                            "total": 31382.051953505576,
+                            "count": 680892,
+                            "self": 29217.357222009934,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 17030.34414549239,
-                                    "count": 5144774,
-                                    "self": 584.6810930130741,
+                                    "total": 2157.2844567964285,
+                                    "count": 680892,
+                                    "self": 76.64871019214206,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 16445.663052479315,
-                                            "count": 9393460,
-                                            "self": 16445.663052479315
+                                            "total": 2080.6357466042864,
+                                            "count": 1252470,
+                                            "self": 2080.6357466042864
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 57.282601641512954,
-                                    "count": 5144774,
+                                    "total": 7.410274699214369,
+                                    "count": 680892,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 340207.1934490865,
-                                            "count": 5144774,
+                                            "total": 237252.86714909453,
+                                            "count": 680892,
                                             "is_parallel": true,
-                                            "self": 282585.79285060236,
+                                            "self": 209447.5869146967,
                                             "children": {
                                                 "steps_from_proto": {
-                                                    "total": 0.27576180009247064,
-                                                    "count": 334,
+                                                    "total": 0.036516600062578064,
+                                                    "count": 48,
                                                     "is_parallel": true,
-                                                    "self": 0.05582819915825876,
+                                                    "self": 0.007270999944183565,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.21993360093421188,
-                                                            "count": 1336,
+                                                            "total": 0.0292456001183945,
+                                                            "count": 192,
                                                             "is_parallel": true,
-                                                            "self": 0.21993360093421188
+                                                            "self": 0.0292456001183945
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 57621.12483668407,
-                                                    "count": 5144774,
+                                                    "total": 27805.24371779777,
+                                                    "count": 680892,
                                                     "is_parallel": true,
-                                                    "self": 4108.40057989971,
+                                                    "self": 512.3516042778283,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 4069.265172227684,
-                                                            "count": 5144774,
+                                                            "total": 527.21155800362,
+                                                            "count": 680892,
                                                             "is_parallel": true,
-                                                            "self": 4069.265172227684
+                                                            "self": 527.21155800362
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 40390.56519020167,
-                                                            "count": 5144774,
+                                                            "total": 25663.8106615048,
+                                                            "count": 680892,
                                                             "is_parallel": true,
-                                                            "self": 40390.56519020167
+                                                            "self": 25663.8106615048
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 9052.893894355,
-                                                            "count": 10289548,
+                                                            "total": 1101.869894011526,
+                                                            "count": 1361784,
                                                             "is_parallel": true,
-                                                            "self": 1798.1079896615674,
+                                                            "self": 216.25630740287716,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 7254.785904693433,
-                                                                    "count": 41158192,
+                                                                    "total": 885.6135866086488,
+                                                                    "count": 5447136,
                                                                     "is_parallel": true,
-                                                                    "self": 7254.785904693433
+                                                                    "self": 885.6135866086488
                                                                 }
                                                             }
                                                         }
@@ -313,31 +313,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 254293.8099800078,
-                            "count": 5144774,
-                            "self": 695.3348793048644,
+                            "total": 205864.19609730496,
+                            "count": 680892,
+                            "self": 91.93224430960254,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 36277.64236250286,
-                                    "count": 5144774,
-                                    "self": 36251.06093480277,
+                                    "total": 86885.65257979528,
+                                    "count": 680892,
+                                    "self": 86882.21135209531,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 26.581427700092036,
-                                            "count": 150,
-                                            "self": 26.581427700092036
+                                            "total": 3.4412276999578353,
+                                            "count": 20,
+                                            "self": 3.4412276999578353
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 217320.83273820006,
-                                    "count": 3639,
-                                    "self": 9005.361679198599,
+                                    "total": 118886.61127320006,
+                                    "count": 485,
+                                    "self": 1067.9659013991914,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 208315.47105900146,
-                                            "count": 109173,
-                                            "self": 208315.47105900146
+                                            "total": 117818.64537180087,
+                                            "count": 14550,
+                                            "self": 117818.64537180087
                                         }
                                     }
                                 }
@@ -346,19 +346,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 7.00005330145359e-07,
+                    "total": 6.00004568696022e-07,
                     "count": 1,
-                    "self": 7.00005330145359e-07
+                    "self": 6.00004568696022e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.16281519999029115,
+                    "total": 0.16298389999428764,
                     "count": 1,
-                    "self": 0.0053425999940373,
+                    "self": 0.005163499998161569,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.15747259999625385,
+                            "total": 0.15782039999612607,
                             "count": 1,
-                            "self": 0.15747259999625385
+                            "self": 0.15782039999612607
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,59 +2,59 @@
     "SoccerTwos": {
         "checkpoints": [
             {
-                "steps": 73499874,
-                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-73499874.onnx",
+                "steps": 83499918,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-83499918.onnx",
                 "reward": 0.0,
-                "creation_time": 1681211045.8793395,
+                "creation_time": 1681461417.7921169,
                 "auxillary_file_paths": [
-                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-73499874.pt"
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-83499918.pt"
                 ]
             },
             {
-                "steps": 73999928,
-                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-73999928.onnx",
+                "steps": 83999982,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-83999982.onnx",
                 "reward": 0.0,
-                "creation_time": 1681213214.429816,
+                "creation_time": 1681463556.34457,
                 "auxillary_file_paths": [
-                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-73999928.pt"
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-83999982.pt"
                 ]
             },
             {
-                "steps": 74499953,
-                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-74499953.onnx",
+                "steps": 84499946,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-84499946.onnx",
                 "reward": 0.0,
-                "creation_time": 1681226168.448455,
+                "creation_time": 1681465745.834339,
                 "auxillary_file_paths": [
-                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-74499953.pt"
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-84499946.pt"
                 ]
             },
             {
-                "steps": 74999941,
-                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-74999941.onnx",
+                "steps": 84999955,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-84999955.onnx",
                 "reward": 0.0,
-                "creation_time": 1681229163.7715986,
+                "creation_time": 1681467909.653306,
                 "auxillary_file_paths": [
-                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-74999941.pt"
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-84999955.pt"
                 ]
             },
             {
-                "steps": 75000024,
-                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-75000024.onnx",
+                "steps": 85000026,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-85000026.onnx",
                 "reward": 0.0,
-                "creation_time": 1681229163.9575994,
+                "creation_time": 1681467909.8272226,
                 "auxillary_file_paths": [
-                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-75000024.pt"
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-85000026.pt"
                 ]
             }
         ],
-        "elo": 1998.0430901658913,
+        "elo": 2004.3327349879148,
         "final_checkpoint": {
-            "steps": 75000024,
+            "steps": 85000026,
             "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1681229163.9575994,
+            "creation_time": 1681467909.8272226,
             "auxillary_file_paths": [
-                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-75000024.pt"
+                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-85000026.pt"
             ]
         }
     },