Overnight Train

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee62440db4333f94907a0ba82a02d9e2394abf9186859d8340e196068812be53
+oid sha256:5ff4363f2bbbd2a930b3344b1f58a93c9bafdf17d3c1add1ab41d976d9750d81
 size 1764633

SoccerTwos/{events.out.tfevents.1682610176.C02FW52PMD6R.9908.0 → SoccerTwos-10000056.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53779abd79c1b842291b471835277e26aa4db27c14c97bb03931e55e2e3beee9
-size 700899
+oid sha256:5ff4363f2bbbd2a930b3344b1f58a93c9bafdf17d3c1add1ab41d976d9750d81
+size 1764633

SoccerTwos/SoccerTwos-10000056.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63059c03286262bf06ab204d70509d3b756dfb281d6ab6bac3110eae9dfbb69b
+size 28421201

SoccerTwos/SoccerTwos-8499908.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40fc5ef7e544ee8ab4a2b1c5e4a0104d36a228fba07db95df90082b53cb53ffe
+size 1764633

SoccerTwos/SoccerTwos-8499908.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69f1bafe00e2d6ea2211fe3af212fb540c9380a4c40f65fd94149610d7c3d945
+size 28421201

SoccerTwos/SoccerTwos-8999992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c49dabbd02fc335d424edf1411471b970737adbdff7e7a4570d9be09b1e56a7
+size 1764633

SoccerTwos/SoccerTwos-8999992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfcd2f76386c73b9de5dc440777c5931bbf8b925355a77fb69b7e4a52d2a4b37
+size 28421201

SoccerTwos/SoccerTwos-9499978.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcecf4e4c03d820d6e867cc5c38af8bc6546ca3ba6ad92ef3d671c69d9f85684
+size 1764633

SoccerTwos/SoccerTwos-9499978.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0de38c0ef95ba500781000e425624aa56adef5f8aae3821847618b4211be0b13
+size 28421201

SoccerTwos/SoccerTwos-9999679.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ff4363f2bbbd2a930b3344b1f58a93c9bafdf17d3c1add1ab41d976d9750d81
+size 1764633

SoccerTwos/SoccerTwos-9999679.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e96fc9b36e9a4a9f4ad412312b1dfec7dfab81ac16c1f99acff5ceb85545ef0b
+size 28421201

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5670f0a897bb59d227a8bd5b7e27157163d7afe1a172482df56af92acb54835
+oid sha256:63059c03286262bf06ab204d70509d3b756dfb281d6ab6bac3110eae9dfbb69b
 size 28421201

SoccerTwos/events.out.tfevents.1682625166.C02FW52PMD6R.27743.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4be2e060d3cec186d8686cb1367d40adae376b4e9f98625c20ebc452ae67fce1
+size 1391315

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": 1000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 10000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos/SoccerTwos.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": 10000000, "time_horizon": 1000, "summary_freq": 75000, "threaded": false, "self_play": {"save_steps": 100000, "team_change": 400000, "swap_steps": 10000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos/SoccerTwos.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}

configuration.yaml

@@ -37,13 +37,13 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1000000
+    max_steps: 10000000
     time_horizon: 1000
-    summary_freq: 10000
+    summary_freq: 75000
     threaded: false
     self_play:
-      save_steps: 50000
-      team_change: 200000
+      save_steps: 100000
+      team_change: 400000
       swap_steps: 10000
       window: 10
       play_against_latest_model_ratio: 0.5

run_logs/Player-0.log

@@ -10,7 +10,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.099 seconds
+- Completed reload, in  0.128 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)
@@ -35,7 +35,7 @@ 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: 1.177457 ms
+UnloadTime: 0.697603 ms
 Registered Communicator in Agent.
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 TOO LONG
@@ -459,12 +459,284 @@ TOO LONG
 TOO LONG
 TOO LONG
 TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+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]: 19393 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 188347 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
@@ -582,7 +854,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 9]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0.7 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 13]
       Initial Block Size 32.0 KB
@@ -627,7 +899,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 10]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 0.7 KB
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 0]
       Initial Block Size 32.0 KB
@@ -661,16 +933,16 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.1 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 19394 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 188348 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]: 19394 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 188348 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.3 MB
+      Peak Allocated memory 17.4 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -699,13 +971,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.1 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 19393 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 188347 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]: 19394 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 188348 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -717,16 +989,16 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.1 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 19394 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 188348 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]: 19393 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 188347 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
-      Peak Allocated memory 3.4 MB
+      Peak Allocated memory 3.0 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
@@ -735,13 +1007,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.1 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 19394 frames
+      Peak usage frame count: [0-1.0 KB]: 188348 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]: 19393 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 188347 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": 3.118328332901001,
-            "min": 3.118328332901001,
-            "max": 3.29575252532959,
-            "count": 100
+            "value": 1.7279229164123535,
+            "min": 1.7279229164123535,
+            "max": 3.289775848388672,
+            "count": 133
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 69551.1953125,
-            "min": 15296.7548828125,
-            "max": 116499.6171875,
-            "count": 100
+            "value": 258939.609375,
+            "min": 258939.609375,
+            "max": 552787.625,
+            "count": 133
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 999.0,
-            "min": 325.2857142857143,
-            "max": 999.0,
-            "count": 100
+            "value": 61.237541528239205,
+            "min": 48.09305373525557,
+            "max": 814.3695652173913,
+            "count": 133
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19980.0,
-            "min": 7992.0,
-            "max": 32820.0,
-            "count": 100
+            "value": 147460.0,
+            "min": 146264.0,
+            "max": 152888.0,
+            "count": 133
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1191.2359573907647,
-            "min": 1190.9857061931052,
-            "max": 1206.4913599520282,
-            "count": 84
+            "value": 1639.2915307065407,
+            "min": 1196.5289883887622,
+            "max": 1646.544195586087,
+            "count": 133
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 2382.4719147815294,
-            "min": 2381.9714123862104,
-            "max": 14452.396868663216,
-            "count": 84
+            "value": 1973707.002970675,
+            "min": 38436.91673612366,
+            "max": 2346348.54834277,
+            "count": 133
         },
         "SoccerTwos.Step.mean": {
-            "value": 999244.0,
-            "min": 9614.0,
-            "max": 999244.0,
-            "count": 100
+            "value": 9974934.0,
+            "min": 74588.0,
+            "max": 9974934.0,
+            "count": 133
         },
         "SoccerTwos.Step.sum": {
-            "value": 999244.0,
-            "min": 9614.0,
-            "max": 999244.0,
-            "count": 100
+            "value": 9974934.0,
+            "min": 74588.0,
+            "max": 9974934.0,
+            "count": 133
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": 0.004696155898272991,
-            "min": -0.03835442662239075,
-            "max": 0.004965650849044323,
-            "count": 100
+            "value": -0.03339169919490814,
+            "min": -0.07884147018194199,
+            "max": 0.1675855964422226,
+            "count": 133
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": 0.04696156084537506,
-            "min": -0.7287341356277466,
-            "max": 0.04965651035308838,
-            "count": 100
+            "value": -40.20360565185547,
+            "min": -82.94122314453125,
+            "max": 213.3364715576172,
+            "count": 133
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.0044372836127877235,
-            "min": -0.04213070869445801,
-            "max": 0.004797778557986021,
-            "count": 100
+            "value": -0.033170223236083984,
+            "min": -0.07947618514299393,
+            "max": 0.16903914511203766,
+            "count": 133
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 0.044372834265232086,
-            "min": -0.7597012519836426,
-            "max": 0.047977786511182785,
-            "count": 100
+            "value": -39.936946868896484,
+            "min": -83.60894775390625,
+            "max": 215.18682861328125,
+            "count": 133
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 100
+            "count": 133
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 100
+            "count": 133
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": 0.0,
-            "min": -0.6666666666666666,
-            "max": 0.27425714262894224,
-            "count": 100
+            "value": -0.060725912550755115,
+            "min": -0.2684082464151776,
+            "max": 0.26833244233457293,
+            "count": 133
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": 0.0,
-            "min": -8.504799962043762,
-            "max": 3.839599996805191,
-            "count": 100
+            "value": -73.11399871110916,
+            "min": -150.45839977264404,
+            "max": 341.5871990919113,
+            "count": 133
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": 0.0,
-            "min": -0.6666666666666666,
-            "max": 0.27425714262894224,
-            "count": 100
+            "value": -0.060725912550755115,
+            "min": -0.2684082464151776,
+            "max": 0.26833244233457293,
+            "count": 133
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": 0.0,
-            "min": -8.504799962043762,
-            "max": 3.839599996805191,
-            "count": 100
-        },
-        "SoccerTwos.IsTraining.mean": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 100
-        },
-        "SoccerTwos.IsTraining.sum": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 100
+            "value": -73.11399871110916,
+            "min": -150.45839977264404,
+            "max": 341.5871990919113,
+            "count": 133
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.016668561093198756,
-            "min": 0.011172198741163205,
-            "max": 0.0236059296488141,
-            "count": 46
+            "value": 0.017163605819930833,
+            "min": 0.013692020925009275,
+            "max": 0.01980743935710052,
+            "count": 133
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.016668561093198756,
-            "min": 0.011172198741163205,
-            "max": 0.0236059296488141,
-            "count": 46
+            "value": 0.0514908174597925,
+            "min": 0.043616841247179156,
+            "max": 0.07922975742840208,
+            "count": 133
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 6.860251111599306e-06,
-            "min": 6.860251111599306e-06,
-            "max": 0.006143144161129991,
-            "count": 46
+            "value": 0.1028438894285096,
+            "min": 0.0019397098630886628,
+            "max": 0.10635385991384586,
+            "count": 133
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 6.860251111599306e-06,
-            "min": 6.860251111599306e-06,
-            "max": 0.006143144161129991,
-            "count": 46
+            "value": 0.3085316682855288,
+            "min": 0.005819129589265989,
+            "max": 0.4254154396553834,
+            "count": 133
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 6.744603797415038e-06,
-            "min": 6.744603797415038e-06,
-            "max": 0.0064106722828000786,
-            "count": 46
+            "value": 0.1049139609767331,
+            "min": 0.001940577875292446,
+            "max": 0.10770234552522501,
+            "count": 133
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 6.744603797415038e-06,
-            "min": 6.744603797415038e-06,
-            "max": 0.0064106722828000786,
-            "count": 46
+            "value": 0.3147418829301993,
+            "min": 0.005821733625877338,
+            "max": 0.43080938210090003,
+            "count": 133
         },
         "SoccerTwos.Policy.LearningRate.mean": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 46
+            "count": 133
         },
         "SoccerTwos.Policy.LearningRate.sum": {
-            "value": 0.0003,
-            "min": 0.0003,
-            "max": 0.0003,
-            "count": 46
+            "value": 0.0009,
+            "min": 0.0009,
+            "max": 0.0012,
+            "count": 133
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.20000000000000007,
-            "min": 0.20000000000000004,
+            "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 46
+            "count": 133
         },
         "SoccerTwos.Policy.Epsilon.sum": {
-            "value": 0.20000000000000007,
-            "min": 0.20000000000000004,
-            "max": 0.20000000000000007,
-            "count": 46
+            "value": 0.6000000000000002,
+            "min": 0.6000000000000002,
+            "max": 0.8000000000000003,
+            "count": 133
         },
         "SoccerTwos.Policy.Beta.mean": {
             "value": 0.005000000000000001,
             "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 46
+            "count": 133
         },
         "SoccerTwos.Policy.Beta.sum": {
-            "value": 0.005000000000000001,
-            "min": 0.005000000000000001,
-            "max": 0.005000000000000001,
-            "count": 46
+            "value": 0.015000000000000003,
+            "min": 0.015000000000000003,
+            "max": 0.020000000000000004,
+            "count": 133
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 133
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 133
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1682610173",
+        "start_time_seconds": "1682625164",
         "python_version": "3.9.16 (main, Mar  8 2023, 04:29:44) \n[Clang 14.0.6 ]",
         "command_line_arguments": "/Users/marshallpostle-floyd/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force",
         "mlagents_version": "0.31.0.dev0",
@@ -204,103 +204,103 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1682613383"
+        "end_time_seconds": "1682662874"
     },
-    "total": 3210.462059139,
+    "total": 37709.464511965,
     "count": 1,
-    "self": 0.28730636499994944,
+    "self": 1.9224007529992377,
     "children": {
         "run_training.setup": {
-            "total": 0.024272067999999924,
+            "total": 0.021891391000000038,
             "count": 1,
-            "self": 0.024272067999999924
+            "self": 0.021891391000000038
         },
         "TrainerController.start_learning": {
-            "total": 3210.150480706,
+            "total": 37707.520219821,
             "count": 1,
-            "self": 1.2297226730402144,
+            "self": 14.835836596554145,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.1976330169994274,
-                    "count": 5,
-                    "self": 3.1976330169994274
+                    "total": 2.6730574149865314,
+                    "count": 25,
+                    "self": 2.6730574149865314
                 },
                 "TrainerController.advance": {
-                    "total": 3205.5478713389602,
-                    "count": 65138,
-                    "self": 1.200474690973806,
+                    "total": 37689.864224052464,
+                    "count": 675837,
+                    "self": 16.304659055022057,
                     "children": {
                         "env_step": {
-                            "total": 964.9150725389877,
-                            "count": 65138,
-                            "self": 796.0277436129908,
+                            "total": 10391.698108468974,
+                            "count": 675837,
+                            "self": 8556.412238605564,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 168.09376654796768,
-                                    "count": 65138,
-                                    "self": 6.892176324938077,
+                                    "total": 1825.7696385712222,
+                                    "count": 675837,
+                                    "self": 81.48673259642987,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 161.2015902230296,
-                                            "count": 129294,
-                                            "self": 161.2015902230296
+                                            "total": 1744.2829059747924,
+                                            "count": 1255662,
+                                            "self": 1744.2829059747924
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.7935623780293035,
-                                    "count": 65138,
+                                    "total": 9.516231292187717,
+                                    "count": 675837,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 3204.265307421,
-                                            "count": 65138,
+                                            "total": 37679.335423007506,
+                                            "count": 675837,
                                             "is_parallel": true,
-                                            "self": 2565.050281008034,
+                                            "self": 30778.31575545263,
                                             "children": {
                                                 "steps_from_proto": {
-                                                    "total": 0.010152164000165609,
-                                                    "count": 10,
+                                                    "total": 0.04989411099655472,
+                                                    "count": 50,
                                                     "is_parallel": true,
-                                                    "self": 0.002122443000757812,
+                                                    "self": 0.01035485201326325,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.008029720999407797,
-                                                            "count": 40,
+                                                            "total": 0.03953925898329147,
+                                                            "count": 200,
                                                             "is_parallel": true,
-                                                            "self": 0.008029720999407797
+                                                            "self": 0.03953925898329147
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 639.2048742489663,
-                                                    "count": 65138,
+                                                    "total": 6900.969773443879,
+                                                    "count": 675837,
                                                     "is_parallel": true,
-                                                    "self": 33.89181430301164,
+                                                    "self": 368.5233629400491,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 21.089855601999822,
-                                                            "count": 65138,
+                                                            "total": 231.55350674922573,
+                                                            "count": 675837,
                                                             "is_parallel": true,
-                                                            "self": 21.089855601999822
+                                                            "self": 231.55350674922573
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 484.15234908301005,
-                                                            "count": 65138,
+                                                            "total": 5218.035794758851,
+                                                            "count": 675837,
                                                             "is_parallel": true,
-                                                            "self": 484.15234908301005
+                                                            "self": 5218.035794758851
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 100.0708552609448,
-                                                            "count": 130276,
+                                                            "total": 1082.8571089957534,
+                                                            "count": 1351674,
                                                             "is_parallel": true,
-                                                            "self": 20.368789272804634,
+                                                            "self": 225.29184557951044,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 79.70206598814016,
-                                                                    "count": 521104,
+                                                                    "total": 857.5652634162429,
+                                                                    "count": 5406696,
                                                                     "is_parallel": true,
-                                                                    "self": 79.70206598814016
+                                                                    "self": 857.5652634162429
                                                                 }
                                                             }
                                                         }
@@ -313,31 +313,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 2239.4323241089987,
-                            "count": 65138,
-                            "self": 8.988694082978327,
+                            "total": 27281.861456528466,
+                            "count": 675837,
+                            "self": 103.76326453801084,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 304.86765934002034,
-                                    "count": 65138,
-                                    "self": 304.48742384402027,
+                                    "total": 3784.0227601554843,
+                                    "count": 675837,
+                                    "self": 3780.493271825492,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.38023549600006845,
-                                            "count": 2,
-                                            "self": 0.38023549600006845
+                                            "total": 3.529488329992546,
+                                            "count": 20,
+                                            "self": 3.529488329992546
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 1925.575970686,
-                                    "count": 46,
-                                    "self": 136.19565102999695,
+                                    "total": 23394.075431834972,
+                                    "count": 481,
+                                    "self": 1476.113508322811,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 1789.380319656003,
-                                            "count": 1389,
-                                            "self": 1789.380319656003
+                                            "total": 21917.96192351216,
+                                            "count": 14439,
+                                            "self": 21917.96192351216
                                         }
                                     }
                                 }
@@ -346,19 +346,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.1490001270431094e-06,
+                    "total": 9.529976523481309e-07,
                     "count": 1,
-                    "self": 1.1490001270431094e-06
+                    "self": 9.529976523481309e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.17525252799987356,
+                    "total": 0.1471008040025481,
                     "count": 1,
-                    "self": 0.003369374000158132,
+                    "self": 0.002914914002758451,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.17188315399971543,
+                            "total": 0.14418588999978965,
                             "count": 1,
-                            "self": 0.17188315399971543
+                            "self": 0.14418588999978965
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,41 +2,59 @@
     "SoccerTwos": {
         "checkpoints": [
             {
-                "steps": 499370,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-499370.onnx",
+                "steps": 8499908,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8499908.onnx",
                 "reward": 0.0,
-                "creation_time": 1682611773.49583,
+                "creation_time": 1682657360.6482089,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-499370.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8499908.pt"
                 ]
             },
             {
-                "steps": 999244,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-999244.onnx",
+                "steps": 8999992,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8999992.onnx",
                 "reward": 0.0,
-                "creation_time": 1682613382.9696581,
+                "creation_time": 1682659233.0955389,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-999244.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8999992.pt"
                 ]
             },
             {
-                "steps": 1000244,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-1000244.onnx",
+                "steps": 9499978,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-9499978.onnx",
                 "reward": 0.0,
-                "creation_time": 1682613383.413217,
+                "creation_time": 1682661082.014508,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-1000244.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-9499978.pt"
+                ]
+            },
+            {
+                "steps": 9999679,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-9999679.onnx",
+                "reward": 0.0,
+                "creation_time": 1682662872.101548,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-9999679.pt"
+                ]
+            },
+            {
+                "steps": 10000056,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-10000056.onnx",
+                "reward": 0.0,
+                "creation_time": 1682662872.351496,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-10000056.pt"
                 ]
             }
         ],
-        "elo": 1191.2359573907647,
+        "elo": 1626.6489360595306,
         "final_checkpoint": {
-            "steps": 1000244,
+            "steps": 10000056,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1682613383.413217,
+            "creation_time": 1682662872.351496,
             "auxillary_file_paths": [
-                "results/SoccerTwos/SoccerTwos/SoccerTwos-1000244.pt"
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-10000056.pt"
             ]
         }
     },