Second push - 8M steps

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee6a4f5463bebcb1265432e5fdf42fdd96ac549b2f2b9ccaa862fadf12da5381
+oid sha256:3f066efc62faff6328c9d8ba986ec5ea4c42d86b6e536824a1382af0900f2b84
 size 2824742

SoccerTwos/{SoccerTwos-499862.onnx → SoccerTwos-3999928.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:997ac80335615cc6853a78e7d9265508c9a0c5eceb27d94fb0502b7be00e0f23
+oid sha256:a2863a40f5f655d0a916358bb354bfe6883849f2d9847af20d62c319f01d3c63
 size 2824742

SoccerTwos/{SoccerTwos-499524.pt → SoccerTwos-3999928.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c42025f0d448a747d4786dd901ccc072ee3af199f8ebd859dd560aca2593bcb5
-size 34750005
+oid sha256:aec7c988cbd65de4a37a46a1e377b34ea161759bc8e7cb691a1b5b422636fbd8
+size 34750155

SoccerTwos/{SoccerTwos-510862.onnx → SoccerTwos-4499974.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee6a4f5463bebcb1265432e5fdf42fdd96ac549b2f2b9ccaa862fadf12da5381
+oid sha256:c2e589d3527b61149722b4dbb200d8bbcc4c9806fb63c0befa48bb77eff67757
 size 2824742

SoccerTwos/{SoccerTwos-499862.pt → SoccerTwos-4499974.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a9c36cf8c238134c34718c9f6ac64204bcb360d23db91f8c9aac4123b22271d
-size 34750005
+oid sha256:fec7a679e8b9c8584803597d8058018067c289fcec59a79323f22c6590fd664e
+size 34750155

SoccerTwos/{events.out.tfevents.1681940178.LAPTOP-T20TBBFH.15460.0 → SoccerTwos-4999963.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30bc5c5512e2975bd9dbb9d5f39bcf687f2dd656e6c0987e10954fb6c0544175
-size 460818
+oid sha256:1b6115abedf562c16bf27e0e1f1c8d8771f2171ed237e4af400294d30febed70
+size 2824742

SoccerTwos/SoccerTwos-4999963.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a42dabc92b2d171d5d06482adc0d9482fba33f5b7c69b76375c6f9d222ffc78b
+size 34750155

SoccerTwos/SoccerTwos-510862.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1a152d6a01b3867d0f9a9900a5779be6634da201e112f9d75b6d6ae34833e537
-size 34750005

SoccerTwos/SoccerTwos-5499967.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e00fd5930f56cf3133edd928ef20d6ccb73b47b5efca1645c3aa3fb8bcec2d6
+size 2824742

SoccerTwos/SoccerTwos-5499967.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c86c2d325d0354e765c5487d8be4ebbe0968d9171d5fb88a11e280034b23652d
+size 34750155

SoccerTwos/SoccerTwos-5999977.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17981144c50bd131f8f2c1fbb3bc835294d8fbec49be0b67fefb8760065e53bf
+size 2824742

SoccerTwos/SoccerTwos-5999977.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2026dc73f4ea5bf915eac080690998b466ec57524f302013aa3a59c30fd4a6bf
+size 34750155

SoccerTwos/SoccerTwos-6499784.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32656c548e57e63f4ef3c079ef32ca578852ca109e82d2126e85f77f0d17a7df
+size 2824742

SoccerTwos/SoccerTwos-6499784.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e888b252b312f11f5aec1151317614b02dfdea717cb5dde179000f5d2600274
+size 34750155

SoccerTwos/SoccerTwos-6999977.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2e3e0e37606d89215e40dbaafc7c13a7f5bb29b000a4c3c4e04dcbf0280c1e8
+size 2824742

SoccerTwos/SoccerTwos-6999977.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1e19a3b41f05e40f08fbd63e2581b4ea77dcbe69f9c8acf0973f5fae540bfec
+size 34750155

SoccerTwos/SoccerTwos-7499964.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02f88f47505937fc8ed01ba13186d824f4ea471bdce24ed5a2d95c8637345ad4
+size 2824742

SoccerTwos/SoccerTwos-7499964.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3737543a07ec608902f08ac486bc43da92c1fb6bab97e3546f07392a25b8468a
+size 34750155

SoccerTwos/SoccerTwos-7999830.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:455bbae1e74edf124158954451d87c1c4b07a5045b342fc1644ec08c74387669
+size 2824742

SoccerTwos/SoccerTwos-7999830.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff1377365002e3cbc3ad2ab961be44a8c981edd39e52140bbd328be5ad72bf76
+size 34750155

SoccerTwos/SoccerTwos-8000034.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f066efc62faff6328c9d8ba986ec5ea4c42d86b6e536824a1382af0900f2b84
+size 2824742

SoccerTwos/SoccerTwos-8000034.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec276decc763acb6ae13fb32ffbc1c0110899f8bfe941394a5964357d73eeb34
+size 34750155

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31743f42fd18cfd0e174f9a7552576d4596254d6a144139db7ceb639bd0e5eae
+oid sha256:1a877ba22fd207baab43975ec982ef7a635ca3b0a8ad4bdcf8fe03cb0a4d57de
 size 34748955

SoccerTwos/events.out.tfevents.1681975264.LAPTOP-T20TBBFH.9376.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d68e0077b4e628543c286af248e9ca4d1f68d092db3d5d0134795b2347b1ae86
+size 157955014

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": true, "hidden_units": 512, "num_layers": 3, "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": 10, "even_checkpoints": false, "max_steps": 5000000, "time_horizon": 1000, "summary_freq": 200, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.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": true, "hidden_units": 512, "num_layers": 3, "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": 10, "even_checkpoints": false, "max_steps": 8000000, "time_horizon": 1000, "summary_freq": 200, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.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_2", "initialize_from": null, "load_model": false, "resume": false, "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: 10
     even_checkpoints: false
-    max_steps: 5000000
+    max_steps: 8000000
     time_horizon: 1000
     summary_freq: 200
     threaded: false
@@ -69,11 +69,11 @@ engine_settings:
   no_graphics: true
 environment_parameters: null
 checkpoint_settings:
-  run_id: SoccerTwos
+  run_id: SoccerTwos_2
   initialize_from: null
   load_model: false
   resume: false
-  force: true
+  force: false
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -9,7 +9,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.161 seconds
+- Completed reload, in 10.466 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)
@@ -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: 0.762700 ms
+UnloadTime: 1.047600 ms
 Registered Communicator in Agent.
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 TOO LONG
@@ -262,12 +262,68 @@ TOO LONG
 TOO LONG
 TOO LONG
 TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+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 4 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]: 9988 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 150953 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
@@ -310,7 +366,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 5]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0.8 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
@@ -385,7 +441,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 2]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 0.8 KB
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 3]
       Initial Block Size 32.0 KB
@@ -419,16 +475,16 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 9989 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 150954 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 5.0 MB
+      Peak Allocated memory 4.9 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 9989 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 150954 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
@@ -457,13 +513,13 @@ 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]: 9988 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 150953 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]: 9989 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 150954 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.6 KB
@@ -475,13 +531,13 @@ 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]: 9989 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 150954 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]: 9988 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 150953 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
@@ -493,13 +549,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 9989 frames
+      Peak usage frame count: [0-1.0 KB]: 150954 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]: 9988 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 150953 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": 3.0548043251037598,
-            "min": 3.0548043251037598,
-            "max": 3.295811891555786,
-            "count": 294
+            "value": 1.6364408731460571,
+            "min": 1.2111297845840454,
+            "max": 3.295790433883667,
+            "count": 29261
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 8113.560546875,
-            "min": 97.88377380371094,
-            "max": 60450.234375,
-            "count": 294
+            "value": 1256.78662109375,
+            "min": 38.75615310668945,
+            "max": 75934.9140625,
+            "count": 29261
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 999.0,
-            "min": 36.0,
+            "value": 107.5,
+            "min": 1.5,
             "max": 999.0,
-            "count": 296
+            "count": 29815
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 3996.0,
-            "min": 144.0,
-            "max": 15984.0,
-            "count": 296
+            "value": 860.0,
+            "min": 12.0,
+            "max": 19980.0,
+            "count": 29815
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1204.8502060098153,
-            "min": 1197.273575898641,
-            "max": 1204.8502060098153,
-            "count": 88
+            "value": 1681.6275089035726,
+            "min": 1189.5147432814815,
+            "max": 1744.6113248627523,
+            "count": 29560
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 2409.7004120196307,
-            "min": 2394.547151797282,
-            "max": 4815.411669907712,
-            "count": 88
+            "value": 6726.51003561429,
+            "min": 2379.029486562963,
+            "max": 23797.706080004307,
+            "count": 29560
         },
         "SoccerTwos.Step.mean": {
-            "value": 509862.0,
-            "min": 155.0,
-            "max": 509862.0,
-            "count": 594
+            "value": 7999830.0,
+            "min": 66.0,
+            "max": 7999830.0,
+            "count": 35757
         },
         "SoccerTwos.Step.sum": {
-            "value": 509862.0,
-            "min": 155.0,
-            "max": 509862.0,
-            "count": 594
+            "value": 7999830.0,
+            "min": 66.0,
+            "max": 7999830.0,
+            "count": 35757
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": -0.0010023899376392365,
-            "min": -0.01649213209748268,
-            "max": 0.07916123420000076,
-            "count": 594
+            "value": -0.2291768193244934,
+            "min": -0.6357744336128235,
+            "max": 0.5942150354385376,
+            "count": 35757
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": -0.0010023899376392365,
-            "min": -0.029721565544605255,
-            "max": 0.14962419867515564,
-            "count": 594
+            "value": -0.2291768193244934,
+            "min": -2.943234920501709,
+            "max": 4.191102027893066,
+            "count": 35757
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.0010758584830909967,
-            "min": -0.019006818532943726,
-            "max": 0.0794139876961708,
-            "count": 594
+            "value": -0.2442202866077423,
+            "min": -0.6416802406311035,
+            "max": 0.6011806726455688,
+            "count": 35757
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -0.0010758584830909967,
-            "min": -0.03164447844028473,
-            "max": 0.15054064989089966,
-            "count": 594
+            "value": -0.2442202866077423,
+            "min": -2.953758955001831,
+            "max": 4.2166595458984375,
+            "count": 35757
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 594
+            "count": 35757
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 594
+            "count": 35757
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": 0.0,
+            "value": -1.0,
             "min": -1.0,
-            "max": 0.9282000064849854,
-            "count": 594
+            "max": 0.9932000041007996,
+            "count": 35757
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": 0.0,
-            "min": -3.0,
-            "max": 2.7360000610351562,
-            "count": 594
+            "value": -1.0,
+            "min": -9.0,
+            "max": 8.780399978160858,
+            "count": 35757
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": 0.0,
+            "value": -1.0,
             "min": -1.0,
-            "max": 0.9282000064849854,
-            "count": 594
+            "max": 0.9932000041007996,
+            "count": 35757
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": 0.0,
-            "min": -3.0,
-            "max": 2.7360000610351562,
-            "count": 594
+            "value": -1.0,
+            "min": -9.0,
+            "max": 8.780399978160858,
+            "count": 35757
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 594
+            "count": 35757
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 594
+            "count": 35757
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.016958356369286776,
-            "min": 0.01292841203782397,
-            "max": 0.02143195556515517,
-            "count": 23
+            "value": 0.023088003506321304,
+            "min": 0.012560889627153907,
+            "max": 0.027914463468672088,
+            "count": 386
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.016958356369286776,
-            "min": 0.01292841203782397,
-            "max": 0.02143195556515517,
-            "count": 23
+            "value": 0.023088003506321304,
+            "min": 0.012560889627153907,
+            "max": 0.027914463468672088,
+            "count": 386
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 8.582447748040067e-07,
-            "min": 8.582447748040067e-07,
-            "max": 0.007309234576920668,
-            "count": 23
+            "value": 0.08402285973230998,
+            "min": 5.7798829341966966e-05,
+            "max": 0.10703929290175437,
+            "count": 386
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 8.582447748040067e-07,
-            "min": 8.582447748040067e-07,
-            "max": 0.007309234576920668,
-            "count": 23
+            "value": 0.08402285973230998,
+            "min": 5.7798829341966966e-05,
+            "max": 0.10703929290175437,
+            "count": 386
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 8.840367001994309e-07,
-            "min": 8.840367001994309e-07,
-            "max": 0.007367936087151369,
-            "count": 23
+            "value": 0.0861522302031517,
+            "min": 5.083439458151891e-05,
+            "max": 0.1108598418533802,
+            "count": 386
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 8.840367001994309e-07,
-            "min": 8.840367001994309e-07,
-            "max": 0.007367936087151369,
-            "count": 23
+            "value": 0.0861522302031517,
+            "min": 5.083439458151891e-05,
+            "max": 0.1108598418533802,
+            "count": 386
         },
         "SoccerTwos.Policy.LearningRate.mean": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 23
+            "count": 386
         },
         "SoccerTwos.Policy.LearningRate.sum": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 23
+            "count": 386
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.20000000000000007,
-            "min": 0.20000000000000007,
+            "min": 0.19999999999999996,
             "max": 0.20000000000000007,
-            "count": 23
+            "count": 386
         },
         "SoccerTwos.Policy.Epsilon.sum": {
             "value": 0.20000000000000007,
-            "min": 0.20000000000000007,
+            "min": 0.19999999999999996,
             "max": 0.20000000000000007,
-            "count": 23
+            "count": 386
         },
         "SoccerTwos.Policy.Beta.mean": {
             "value": 0.005000000000000001,
-            "min": 0.005000000000000001,
+            "min": 0.005,
             "max": 0.005000000000000001,
-            "count": 23
+            "count": 386
         },
         "SoccerTwos.Policy.Beta.sum": {
             "value": 0.005000000000000001,
-            "min": 0.005000000000000001,
+            "min": 0.005,
             "max": 0.005000000000000001,
-            "count": 23
+            "count": 386
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1681940172",
+        "start_time_seconds": "1681975243",
         "python_version": "3.9.16 (main, Mar  8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]",
-        "command_line_arguments": "C:\\Users\\andre\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force",
+        "command_line_arguments": "C:\\Users\\andre\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos_2 --no-graphics",
         "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": "1681943113"
+        "end_time_seconds": "1682024082"
     },
-    "total": 2940.9553363,
+    "total": 48839.2381127,
     "count": 1,
-    "self": 4.237974200000281,
+    "self": 1.5360641999941436,
     "children": {
         "run_training.setup": {
-            "total": 0.16140380000000043,
+            "total": 0.23951239999999885,
             "count": 1,
-            "self": 0.16140380000000043
+            "self": 0.23951239999999885
         },
         "TrainerController.start_learning": {
-            "total": 2936.5559583,
+            "total": 48837.4625361,
             "count": 1,
-            "self": 1.0653708999902847,
+            "self": 18.071318898437312,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 5.959613299999947,
-                    "count": 3,
-                    "self": 5.959613299999947
+                    "total": 22.469729600012784,
+                    "count": 40,
+                    "self": 22.469729600012784
                 },
                 "TrainerController.advance": {
-                    "total": 2929.2545971000095,
-                    "count": 33518,
-                    "self": 1.2151851000153329,
+                    "total": 48796.55171660154,
+                    "count": 544485,
+                    "self": 18.84643090087775,
                     "children": {
                         "env_step": {
-                            "total": 919.9859469999996,
-                            "count": 33518,
-                            "self": 650.6468326999602,
+                            "total": 13480.940880298956,
+                            "count": 544485,
+                            "self": 9624.141251096935,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 268.6023134000405,
-                                    "count": 33518,
-                                    "self": 7.664491400039651,
+                                    "total": 3845.350842202946,
+                                    "count": 544485,
+                                    "self": 125.70891010125706,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 260.93782200000084,
-                                            "count": 66594,
-                                            "self": 260.93782200000084
+                                            "total": 3719.641932101689,
+                                            "count": 1006372,
+                                            "self": 3719.641932101689
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.7368008999989186,
-                                    "count": 33517,
+                                    "total": 11.44878699907548,
+                                    "count": 544485,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2929.0946689999982,
-                                            "count": 33517,
+                                            "total": 48790.7222916014,
+                                            "count": 544485,
                                             "is_parallel": true,
-                                            "self": 2422.0422877000096,
+                                            "self": 41243.46022880326,
                                             "children": {
                                                 "steps_from_proto": {
-                                                    "total": 0.008762400000048132,
-                                                    "count": 6,
+                                                    "total": 0.10577209997159187,
+                                                    "count": 80,
                                                     "is_parallel": true,
-                                                    "self": 0.0018253999989479297,
+                                                    "self": 0.021406299991507893,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.006937000001100202,
-                                                            "count": 24,
+                                                            "total": 0.08436579998008398,
+                                                            "count": 320,
                                                             "is_parallel": true,
-                                                            "self": 0.006937000001100202
+                                                            "self": 0.08436579998008398
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 507.04361889998864,
-                                                    "count": 33517,
+                                                    "total": 7547.156290698165,
+                                                    "count": 544485,
                                                     "is_parallel": true,
-                                                    "self": 29.17730169997418,
+                                                    "self": 433.1522372964082,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 26.5791723999651,
-                                                            "count": 33517,
+                                                            "total": 388.46125400078466,
+                                                            "count": 544485,
                                                             "is_parallel": true,
-                                                            "self": 26.5791723999651
+                                                            "self": 388.46125400078466
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 359.4772035000106,
-                                                            "count": 33517,
+                                                            "total": 5352.378265900363,
+                                                            "count": 544485,
                                                             "is_parallel": true,
-                                                            "self": 359.4772035000106
+                                                            "self": 5352.378265900363
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 91.80994130003873,
-                                                            "count": 67034,
+                                                            "total": 1373.1645335006097,
+                                                            "count": 1088970,
                                                             "is_parallel": true,
-                                                            "self": 18.595545700032517,
+                                                            "self": 279.40359070710474,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 73.21439560000621,
-                                                                    "count": 268136,
+                                                                    "total": 1093.760942793505,
+                                                                    "count": 4355880,
                                                                     "is_parallel": true,
-                                                                    "self": 73.21439560000621
+                                                                    "self": 1093.760942793505
                                                                 }
                                                             }
                                                         }
@@ -313,31 +313,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 2008.0534649999945,
-                            "count": 33517,
-                            "self": 7.761995500015246,
+                            "total": 35296.76440540171,
+                            "count": 544485,
+                            "self": 131.58449890200427,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 267.5684381999786,
-                                    "count": 33517,
-                                    "self": 267.2045784999782,
+                                    "total": 6924.779084599799,
+                                    "count": 544485,
+                                    "self": 6919.675474399804,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.3638597000003756,
-                                            "count": 1,
-                                            "self": 0.3638597000003756
+                                            "total": 5.103610199994364,
+                                            "count": 16,
+                                            "self": 5.103610199994364
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 1732.7230313000007,
-                                    "count": 23,
-                                    "self": 121.67005469999913,
+                                    "total": 28240.400821899908,
+                                    "count": 386,
+                                    "self": 1867.136166400087,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 1611.0529766000016,
-                                            "count": 690,
-                                            "self": 1611.0529766000016
+                                            "total": 26373.26465549982,
+                                            "count": 11598,
+                                            "self": 26373.26465549982
                                         }
                                     }
                                 }
@@ -346,19 +346,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.8999999156221747e-06,
+                    "total": 1.500004145782441e-06,
                     "count": 1,
-                    "self": 1.8999999156221747e-06
+                    "self": 1.500004145782441e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.27637510000022303,
+                    "total": 0.3697695000009844,
                     "count": 1,
-                    "self": 0.014586900000267633,
+                    "self": 0.07219520000217017,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.2617881999999554,
+                            "total": 0.29757429999881424,
                             "count": 1,
-                            "self": 0.2617881999999554
+                            "self": 0.29757429999881424
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,32 +2,104 @@
     "SoccerTwos": {
         "checkpoints": [
             {
-                "steps": 499862,
-                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-499862.onnx",
+                "steps": 3999928,
+                "file_path": "results\\SoccerTwos_2\\SoccerTwos\\SoccerTwos-3999928.onnx",
                 "reward": 0.0,
-                "creation_time": 1681943089.075542,
+                "creation_time": 1681997978.807382,
                 "auxillary_file_paths": [
-                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-499862.pt"
+                    "results\\SoccerTwos_2\\SoccerTwos\\SoccerTwos-3999928.pt"
                 ]
             },
             {
-                "steps": 510862,
-                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-510862.onnx",
+                "steps": 4499974,
+                "file_path": "results\\SoccerTwos_2\\SoccerTwos\\SoccerTwos-4499974.onnx",
                 "reward": 0.0,
-                "creation_time": 1681943109.540527,
+                "creation_time": 1682000730.703229,
                 "auxillary_file_paths": [
-                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-510862.pt"
+                    "results\\SoccerTwos_2\\SoccerTwos\\SoccerTwos-4499974.pt"
+                ]
+            },
+            {
+                "steps": 4999963,
+                "file_path": "results\\SoccerTwos_2\\SoccerTwos\\SoccerTwos-4999963.onnx",
+                "reward": 0.0,
+                "creation_time": 1682003569.506058,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos_2\\SoccerTwos\\SoccerTwos-4999963.pt"
+                ]
+            },
+            {
+                "steps": 5499967,
+                "file_path": "results\\SoccerTwos_2\\SoccerTwos\\SoccerTwos-5499967.onnx",
+                "reward": 0.0,
+                "creation_time": 1682006722.1011825,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos_2\\SoccerTwos\\SoccerTwos-5499967.pt"
+                ]
+            },
+            {
+                "steps": 5999977,
+                "file_path": "results\\SoccerTwos_2\\SoccerTwos\\SoccerTwos-5999977.onnx",
+                "reward": 0.0,
+                "creation_time": 1682009895.4905791,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos_2\\SoccerTwos\\SoccerTwos-5999977.pt"
+                ]
+            },
+            {
+                "steps": 6499784,
+                "file_path": "results\\SoccerTwos_2\\SoccerTwos\\SoccerTwos-6499784.onnx",
+                "reward": 0.0,
+                "creation_time": 1682013091.5564399,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos_2\\SoccerTwos\\SoccerTwos-6499784.pt"
+                ]
+            },
+            {
+                "steps": 6999977,
+                "file_path": "results\\SoccerTwos_2\\SoccerTwos\\SoccerTwos-6999977.onnx",
+                "reward": 0.0,
+                "creation_time": 1682016254.8704953,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos_2\\SoccerTwos\\SoccerTwos-6999977.pt"
+                ]
+            },
+            {
+                "steps": 7499964,
+                "file_path": "results\\SoccerTwos_2\\SoccerTwos\\SoccerTwos-7499964.onnx",
+                "reward": 0.0,
+                "creation_time": 1682019471.8597865,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos_2\\SoccerTwos\\SoccerTwos-7499964.pt"
+                ]
+            },
+            {
+                "steps": 7999830,
+                "file_path": "results\\SoccerTwos_2\\SoccerTwos\\SoccerTwos-7999830.onnx",
+                "reward": 0.0,
+                "creation_time": 1682024080.2274048,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos_2\\SoccerTwos\\SoccerTwos-7999830.pt"
+                ]
+            },
+            {
+                "steps": 8000034,
+                "file_path": "results\\SoccerTwos_2\\SoccerTwos\\SoccerTwos-8000034.onnx",
+                "reward": 0.0,
+                "creation_time": 1682024080.6364968,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos_2\\SoccerTwos\\SoccerTwos-8000034.pt"
                 ]
             }
         ],
-        "elo": 1204.8502060098153,
+        "elo": 1680.8968248947117,
         "final_checkpoint": {
-            "steps": 510862,
-            "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
+            "steps": 8000034,
+            "file_path": "results\\SoccerTwos_2\\SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1681943109.540527,
+            "creation_time": 1682024080.6364968,
             "auxillary_file_paths": [
-                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-510862.pt"
+                "results\\SoccerTwos_2\\SoccerTwos\\SoccerTwos-8000034.pt"
             ]
         }
     },