18th Push

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e548b98cec70c6be0928cb54d3e302bf0b6f36f3c196795d13eaa5e5ccd0de79
+oid sha256:8f261768320c964ea38a666e212e93438b4d92b8accad81f54af79e5f6655396
 size 2351062

SoccerTwos/SoccerTwos-116482066.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f261768320c964ea38a666e212e93438b4d92b8accad81f54af79e5f6655396
+size 2351062

SoccerTwos/SoccerTwos-116482066.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13eaaf228c175fb7f251b8ede6ba0dabacb8480fdd402bab312beb4b13d63a8c
+size 36303358

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1a57ee2f8c6f84015679e2c1d67cbf1eae1bb1db78acc31c034024bf437bc30
+oid sha256:ec134a06984c01628bd71b88365f672637f8440c7d108fdc05c0350c655b6062
 size 36301318

SoccerTwos/events.out.tfevents.1725991963.Bretts-MacBook-Pro.local.9961.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0984d5c1e2b06455906e92152c1e225f8a84074f0ec416ba3869e394dd85b13
-size 1225321
+oid sha256:94971e98c252251fa40536efba42540a0354875aa25aca117757d24b0e33c648
+size 2343599

SoccerTwos/events.out.tfevents.1726018316.Bretts-MBP.home.81084.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18662e1cbf117a3f39b6588f19ea9f686ad6239318f7ba6f41da4df3d137b426
+size 9359795

SoccerTwos/events.out.tfevents.1726062834.Bretts-MacBook-Pro.local.87413.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e4d307c05608bd53ebb7348a6ec607704ff2fb80cdbf4731a0303410fdab53a
+size 3071775

SoccerTwos/events.out.tfevents.1726080022.Bretts-MacBook-Pro.local.90333.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efe0dadea4fc20cc436002e2f7bd82852512b58245e77fa3f784bb4ec9257629
+size 2185347

SoccerTwos/events.out.tfevents.1726173529.Bretts-MacBook-Pro.local.97078.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b19f0c18d0d9baa9591ef2bac3a364eec44402d4000408bc95fd3b396535e8ca
+size 17019522

SoccerTwos/events.out.tfevents.1726243071.Bretts-MacBook-Pro.local.13986.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f36714ac72094d619d4bd2eb578110bf18dec90bf2ee8a58683db4d06cc1e3c2
+size 4517072

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 40960, "buffer_size": 163840, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.9, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "linear", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": {"sequence_length": 16, "memory_size": 128}, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "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}}, "curiosity": {"gamma": 0.9, "strength": 1e-06, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0003, "encoding_size": 512}, "rnd": {"gamma": 0.9, "strength": 1e-06, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 1, "even_checkpoints": false, "max_steps": 80000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 100000, "team_change": 400000, "swap_steps": 2000, "window": 30, "play_against_latest_model_ratio": 0.5, "initial_elo": 1.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./SoccerTwos/SoccerTwos.app", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "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, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "sept-run-01", "initialize_from": null, "load_model": false, "resume": true, "force": false, "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": 40960, "buffer_size": 163840, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.9, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "linear", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": {"sequence_length": 16, "memory_size": 128}, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.999, "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}}, "curiosity": {"gamma": 0.9, "strength": 1e-06, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0003, "encoding_size": 512}, "rnd": {"gamma": 0.9, "strength": 1e-06, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 1, "even_checkpoints": false, "max_steps": 10000000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 100000, "team_change": 400000, "swap_steps": 2000, "window": 30, "play_against_latest_model_ratio": 0.9, "initial_elo": 1.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./SoccerTwos/SoccerTwos.app", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "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, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "sept-run-01", "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

@@ -26,7 +26,7 @@ behaviors:
       deterministic: false
     reward_signals:
       extrinsic:
-        gamma: 0.995
+        gamma: 0.999
         strength: 1.0
         network_settings:
           normalize: false
@@ -65,7 +65,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 1
     even_checkpoints: false
-    max_steps: 80000000
+    max_steps: 10000000000
     time_horizon: 1000
     summary_freq: 10000
     threaded: false
@@ -74,7 +74,7 @@ behaviors:
       team_change: 400000
       swap_steps: 2000
       window: 30
-      play_against_latest_model_ratio: 0.5
+      play_against_latest_model_ratio: 0.9
       initial_elo: 1.0
     behavioral_cloning: null
 env_settings:

run_logs/Player-0.log

@@ -10,7 +10,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.298 seconds
+- Completed reload, in  0.048 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)
@@ -35,6 +35,285 @@ 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: 1.378958 ms
+UnloadTime: 0.352792 ms
 Registered Communicator in Agent.
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Default audio device was changed, but the audio system failed to initialize it. Attempting to reset sound system.
+Thread 0x16d3eb000 may have been prematurely finalized
+Setting up 7 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]: 80425 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
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 128 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 78.8 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 7
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 13
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 9]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 8]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_OSX HID Input]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.7 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 10]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 11]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 12]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 13
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 80426 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      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]: 80426 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.5 MB
+      Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 80425 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]: 80426 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 173.5 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 80426 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]: 80425 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 Large allocation bytes 0 B
+[ALLOC_TYPETREE] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 80426 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]: 80425 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
+      Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -2,309 +2,309 @@
     "name": "root",
     "gauges": {
         "SoccerTwos.Policy.Entropy.mean": {
-            "value": 1.5399205684661865,
-            "min": 1.512854814529419,
-            "max": 1.568915843963623,
-            "count": 205
+            "value": 2.413952589035034,
+            "min": 2.355649948120117,
+            "max": 2.436649799346924,
+            "count": 428
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 33410.1171875,
-            "min": 16442.71484375,
-            "max": 34939.3828125,
-            "count": 205
+            "value": 48742.53125,
+            "min": 40293.83203125,
+            "max": 57293.578125,
+            "count": 428
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 68.73611111111111,
-            "min": 50.714285714285715,
-            "max": 97.9,
-            "count": 205
+            "value": 72.26470588235294,
+            "min": 50.597938144329895,
+            "max": 96.53846153846153,
+            "count": 428
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19796.0,
-            "min": 8296.0,
-            "max": 20428.0,
-            "count": 205
+            "value": 19656.0,
+            "min": 17320.0,
+            "max": 20940.0,
+            "count": 428
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 272.7278779503926,
-            "min": 233.8647348324593,
-            "max": 300.1237163905635,
-            "count": 205
+            "value": 200.5846644937817,
+            "min": 200.5846644937817,
+            "max": 255.10006908123884,
+            "count": 428
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 39272.81442485654,
-            "min": 19555.710165917008,
-            "max": 53458.99614819349,
-            "count": 205
+            "value": 27279.514371154313,
+            "min": 22310.68126471372,
+            "max": 45997.356734281755,
+            "count": 428
         },
         "SoccerTwos.Step.mean": {
-            "value": 79999942.0,
-            "min": 77959890.0,
-            "max": 79999942.0,
-            "count": 205
+            "value": 116479979.0,
+            "min": 112209978.0,
+            "max": 116479979.0,
+            "count": 428
         },
         "SoccerTwos.Step.sum": {
-            "value": 79999942.0,
-            "min": 77959890.0,
-            "max": 79999942.0,
-            "count": 205
+            "value": 116479979.0,
+            "min": 112209978.0,
+            "max": 116479979.0,
+            "count": 428
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": -0.13813956081867218,
-            "min": -0.20680981874465942,
-            "max": 0.12538133561611176,
-            "count": 205
+            "value": -0.18372218310832977,
+            "min": -0.19437754154205322,
+            "max": 0.12453540414571762,
+            "count": 428
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": -19.89209747314453,
-            "min": -29.84649658203125,
-            "max": 23.822452545166016,
-            "count": 205
+            "value": -25.169939041137695,
+            "min": -34.03402328491211,
+            "max": 19.427522659301758,
+            "count": 428
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.1384831964969635,
-            "min": -0.2039821445941925,
-            "max": 0.12654316425323486,
-            "count": 205
+            "value": -0.18120113015174866,
+            "min": -0.19503891468048096,
+            "max": 0.12437755614519119,
+            "count": 428
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -19.941579818725586,
-            "min": -29.398372650146484,
-            "max": 24.043201446533203,
-            "count": 205
+            "value": -24.824554443359375,
+            "min": -33.5821647644043,
+            "max": 19.29033851623535,
+            "count": 428
         },
         "SoccerTwos.Policy.CuriosityBaselineEstimate.mean": {
-            "value": 0.00017744496290106326,
-            "min": -1.280401829717448e-05,
-            "max": 0.00034355284878984094,
-            "count": 205
+            "value": 0.00013197257067076862,
+            "min": -4.9894701078301296e-05,
+            "max": 0.00027073908131569624,
+            "count": 428
         },
         "SoccerTwos.Policy.CuriosityBaselineEstimate.sum": {
-            "value": 0.02555207535624504,
-            "min": -0.000870673218742013,
-            "max": 0.05909109115600586,
-            "count": 205
+            "value": 0.018080241978168488,
+            "min": -0.007733678445219994,
+            "max": 0.04207998514175415,
+            "count": 428
         },
         "SoccerTwos.Policy.CuriosityValueEstimate.mean": {
-            "value": 0.00018491833179723471,
-            "min": -8.266243639809545e-06,
-            "max": 0.00034810250508598983,
-            "count": 205
+            "value": 0.0001415555307175964,
+            "min": -5.4355001338990405e-05,
+            "max": 0.0002652776020113379,
+            "count": 428
         },
         "SoccerTwos.Policy.CuriosityValueEstimate.sum": {
-            "value": 0.026628239080309868,
-            "min": -0.0005621045711450279,
-            "max": 0.05987362936139107,
-            "count": 205
+            "value": 0.019393106922507286,
+            "min": -0.008425025269389153,
+            "max": 0.04132426530122757,
+            "count": 428
         },
         "SoccerTwos.Policy.RndBaselineEstimate.mean": {
-            "value": 1.5067198546603322e-05,
-            "min": -0.0004950298462063074,
-            "max": 9.06805507838726e-05,
-            "count": 205
+            "value": 9.664618119131774e-06,
+            "min": -6.639550701947883e-05,
+            "max": 5.97319558437448e-05,
+            "count": 428
         },
         "SoccerTwos.Policy.RndBaselineEstimate.sum": {
-            "value": 0.0021696765907108784,
-            "min": -0.03429080545902252,
-            "max": 0.015687735751271248,
-            "count": 205
+            "value": 0.0013240526895970106,
+            "min": -0.009162579663097858,
+            "max": 0.008302741684019566,
+            "count": 428
         },
         "SoccerTwos.Policy.RndValueEstimate.mean": {
-            "value": 1.4539382391376421e-05,
-            "min": -0.0005132480873726308,
-            "max": 8.886260911822319e-05,
-            "count": 205
+            "value": 1.0724314051913098e-05,
+            "min": -7.216515950858593e-05,
+            "max": 5.9375102864578366e-05,
+            "count": 428
         },
         "SoccerTwos.Policy.RndValueEstimate.sum": {
-            "value": 0.0020936711225658655,
-            "min": -0.03490087017416954,
-            "max": 0.0153732318431139,
-            "count": 205
+            "value": 0.0014692309778183699,
+            "min": -0.009958792477846146,
+            "max": 0.008253139443695545,
+            "count": 428
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 205
+            "count": 428
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 205
+            "count": 428
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.11527777794334623,
-            "min": -0.3677196840601643,
-            "max": 0.27121262989546124,
-            "count": 205
+            "value": -0.30921314058512667,
+            "min": -0.34116986434753627,
+            "max": 0.3086177231390265,
+            "count": 428
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -16.600000023841858,
-            "min": -60.78120017051697,
-            "max": 51.530399680137634,
-            "count": 205
+            "value": -42.36220026016235,
+            "min": -49.810800194740295,
+            "max": 48.76160025596619,
+            "count": 428
         },
         "SoccerTwos.Policy.CuriosityReward.mean": {
-            "value": 3.116804232582303e-06,
+            "value": 2.8015310108358346e-06,
             "min": 0.0,
-            "max": 5.3372595253514096e-06,
-            "count": 205
+            "max": 7.618662638938426e-06,
+            "count": 428
         },
         "SoccerTwos.Policy.CuriosityReward.sum": {
-            "value": 0.00044881980949185163,
+            "value": 0.00038380974848450933,
             "min": 0.0,
-            "max": 0.0007159653786175113,
-            "count": 205
+            "max": 0.0010100169779150292,
+            "count": 428
         },
         "SoccerTwos.Policy.RndReward.mean": {
-            "value": 1.269147985717546e-06,
-            "min": 8.895423654938608e-07,
-            "max": 1.867236133108463e-06,
-            "count": 205
+            "value": 1.3432801519607946e-06,
+            "min": 8.947482167043677e-07,
+            "max": 1.7273090733738172e-06,
+            "count": 428
         },
         "SoccerTwos.Policy.RndReward.sum": {
-            "value": 0.00018275730994332662,
-            "min": 7.041936916607483e-05,
-            "max": 0.00019470762803308617,
-            "count": 205
+            "value": 0.00018402938081862885,
+            "min": 0.00015929336030495733,
+            "max": 0.00019037561346024745,
+            "count": 428
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.11527777794334623,
-            "min": -0.3677196840601643,
-            "max": 0.27121262989546124,
-            "count": 205
+            "value": -0.30921314058512667,
+            "min": -0.34116986434753627,
+            "max": 0.3086177231390265,
+            "count": 428
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -16.600000023841858,
-            "min": -60.78120017051697,
-            "max": 51.530399680137634,
-            "count": 205
+            "value": -42.36220026016235,
+            "min": -49.810800194740295,
+            "max": 48.76160025596619,
+            "count": 428
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 205
+            "count": 428
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 205
+            "count": 428
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.012351180444966303,
-            "min": 0.0067968835305691755,
-            "max": 0.015325144719099626,
-            "count": 13
+            "value": 0.010974738972436171,
+            "min": 0.006480928104186508,
+            "max": 0.017731858902455617,
+            "count": 28
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.012351180444966303,
-            "min": 0.0067968835305691755,
-            "max": 0.015325144719099626,
-            "count": 13
+            "value": 0.010974738972436171,
+            "min": 0.006480928104186508,
+            "max": 0.017731858902455617,
+            "count": 28
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.0175623488612473,
-            "min": 0.016617532974729936,
-            "max": 0.0175623488612473,
-            "count": 13
+            "value": 0.01760079540933172,
+            "min": 0.017158242408186197,
+            "max": 0.020099001626173656,
+            "count": 28
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.0175623488612473,
-            "min": 0.016617532974729936,
-            "max": 0.0175623488612473,
-            "count": 13
+            "value": 0.01760079540933172,
+            "min": 0.017158242408186197,
+            "max": 0.020099001626173656,
+            "count": 28
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.018047905527055264,
-            "min": 0.017212544723103445,
-            "max": 0.018047905527055264,
-            "count": 13
+            "value": 0.01818520234276851,
+            "min": 0.017673577802876633,
+            "max": 0.02067598778133591,
+            "count": 28
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.018047905527055264,
-            "min": 0.017212544723103445,
-            "max": 0.018047905527055264,
-            "count": 13
+            "value": 0.01818520234276851,
+            "min": 0.017673577802876633,
+            "max": 0.02067598778133591,
+            "count": 28
         },
         "SoccerTwos.Policy.LearningRate.mean": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 13
+            "count": 28
         },
         "SoccerTwos.Policy.LearningRate.sum": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 13
+            "count": 28
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.20000000000000004,
             "min": 0.20000000000000004,
             "max": 0.20000000000000004,
-            "count": 13
+            "count": 28
         },
         "SoccerTwos.Policy.Epsilon.sum": {
             "value": 0.20000000000000004,
             "min": 0.20000000000000004,
             "max": 0.20000000000000004,
-            "count": 13
+            "count": 28
         },
         "SoccerTwos.Policy.Beta.mean": {
-            "value": 2.5267467249999682e-05,
-            "min": 2.5267467249999682e-05,
-            "max": 0.0002468431697500002,
-            "count": 13
+            "value": 0.009883782196138,
+            "min": 0.009883782196138,
+            "max": 0.009887763606742,
+            "count": 28
         },
         "SoccerTwos.Policy.Beta.sum": {
-            "value": 2.5267467249999682e-05,
-            "min": 2.5267467249999682e-05,
-            "max": 0.0002468431697500002,
-            "count": 13
+            "value": 0.009883782196138,
+            "min": 0.009883782196138,
+            "max": 0.009887763606742,
+            "count": 28
         },
         "SoccerTwos.Losses.CuriosityForwardLoss.mean": {
-            "value": 0.04501075980563959,
-            "min": 0.044811712888379894,
-            "max": 0.12417677200088899,
-            "count": 13
+            "value": 0.03778785094618797,
+            "min": 0.03734184770534436,
+            "max": 0.1971647860482335,
+            "count": 28
         },
         "SoccerTwos.Losses.CuriosityForwardLoss.sum": {
-            "value": 0.04501075980563959,
-            "min": 0.044811712888379894,
-            "max": 0.12417677200088899,
-            "count": 13
+            "value": 0.03778785094618797,
+            "min": 0.03734184770534436,
+            "max": 0.1971647860482335,
+            "count": 28
         },
         "SoccerTwos.Losses.CuriosityInverseLoss.mean": {
-            "value": 1.1322325964768727,
-            "min": 1.1322325964768727,
-            "max": 1.3759111762046814,
-            "count": 13
+            "value": 1.6315673093001049,
+            "min": 1.6234056651592255,
+            "max": 2.092972139517466,
+            "count": 28
         },
         "SoccerTwos.Losses.CuriosityInverseLoss.sum": {
-            "value": 1.1322325964768727,
-            "min": 1.1322325964768727,
-            "max": 1.3759111762046814,
-            "count": 13
+            "value": 1.6315673093001049,
+            "min": 1.6234056651592255,
+            "max": 2.092972139517466,
+            "count": 28
         },
         "SoccerTwos.Losses.RNDLoss.mean": {
-            "value": 0.016439350321888924,
-            "min": 0.0163416750729084,
-            "max": 0.01815606839954853,
-            "count": 13
+            "value": 0.015613269060850143,
+            "min": 0.015565264038741589,
+            "max": 0.017592713236808777,
+            "count": 28
         },
         "SoccerTwos.Losses.RNDLoss.sum": {
-            "value": 0.016439350321888924,
-            "min": 0.0163416750729084,
-            "max": 0.01815606839954853,
-            "count": 13
+            "value": 0.015613269060850143,
+            "min": 0.015565264038741589,
+            "max": 0.017592713236808777,
+            "count": 28
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1725978587",
+        "start_time_seconds": "1726243068",
         "python_version": "3.10.12 (main, Aug 23 2024, 16:29:11) [Clang 15.0.0 (clang-1500.3.9.4)]",
         "command_line_arguments": "/Users/brettgohre/Desktop/huggingface/ml-agents/games/bin/mlagents-learn ./config/poca/sept/three.yaml --env=./SoccerTwos/SoccerTwos.app --run-id=sept-run-01 --resume --no-graphics",
         "mlagents_version": "1.1.0.dev0",
@@ -312,103 +312,103 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.4.0",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1725986627"
+        "end_time_seconds": "1726260795"
     },
-    "total": 8040.06352700002,
+    "total": 16904.79020066606,
     "count": 1,
-    "self": 0.23776454094331712,
+    "self": 0.167630082112737,
     "children": {
         "run_training.setup": {
-            "total": 0.019753542030230165,
+            "total": 0.023219667025841773,
             "count": 1,
-            "self": 0.019753542030230165
+            "self": 0.023219667025841773
         },
         "TrainerController.start_learning": {
-            "total": 8039.806008917047,
+            "total": 16904.59935091692,
             "count": 1,
-            "self": 1.314517370716203,
+            "self": 2.453233522363007,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.6344570019864477,
-                    "count": 7,
-                    "self": 3.6344570019864477
+                    "total": 3.8081024570856243,
+                    "count": 12,
+                    "self": 3.8081024570856243
                 },
                 "TrainerController.advance": {
-                    "total": 8034.724037919368,
-                    "count": 140117,
-                    "self": 1.1400749064050615,
+                    "total": 16898.104903812404,
+                    "count": 293343,
+                    "self": 2.2329050848493353,
                     "children": {
                         "env_step": {
-                            "total": 5695.069258543197,
-                            "count": 140117,
-                            "self": 5497.789965885109,
+                            "total": 11851.946922125062,
+                            "count": 293343,
+                            "self": 11464.108450845582,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 196.4914063619217,
-                                    "count": 140117,
-                                    "self": 8.097888264048379,
+                                    "total": 386.3168923628982,
+                                    "count": 293343,
+                                    "self": 15.735434583271854,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 188.3935180978733,
-                                            "count": 256298,
-                                            "self": 188.3935180978733
+                                            "total": 370.58145777962636,
+                                            "count": 536174,
+                                            "self": 370.58145777962636
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.7878862961661071,
-                                    "count": 140117,
+                                    "total": 1.5215789165813476,
+                                    "count": 293343,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 8034.413471959007,
-                                            "count": 140117,
+                                            "total": 16897.44152066519,
+                                            "count": 293343,
                                             "is_parallel": true,
-                                            "self": 2685.770048620354,
+                                            "self": 5736.2697331981035,
                                             "children": {
                                                 "steps_from_proto": {
-                                                    "total": 0.009649291925597936,
-                                                    "count": 14,
+                                                    "total": 0.016120707150548697,
+                                                    "count": 24,
                                                     "is_parallel": true,
-                                                    "self": 0.0013223288697190583,
+                                                    "self": 0.0021714119939133525,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.008326963055878878,
-                                                            "count": 56,
+                                                            "total": 0.013949295156635344,
+                                                            "count": 96,
                                                             "is_parallel": true,
-                                                            "self": 0.008326963055878878
+                                                            "self": 0.013949295156635344
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 5348.633774046728,
-                                                    "count": 140117,
+                                                    "total": 11161.155666759936,
+                                                    "count": 293343,
                                                     "is_parallel": true,
-                                                    "self": 13.765971858112607,
+                                                    "self": 28.08294066612143,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 104.13079777162056,
-                                                            "count": 140117,
+                                                            "total": 219.95445196295623,
+                                                            "count": 293343,
                                                             "is_parallel": true,
-                                                            "self": 104.13079777162056
+                                                            "self": 219.95445196295623
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 5057.198739988089,
-                                                            "count": 140117,
+                                                            "total": 10553.74234917364,
+                                                            "count": 293343,
                                                             "is_parallel": true,
-                                                            "self": 5057.198739988089
+                                                            "self": 10553.74234917364
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 173.53826442890568,
-                                                            "count": 280234,
+                                                            "total": 359.37592495721765,
+                                                            "count": 586686,
                                                             "is_parallel": true,
-                                                            "self": 20.749318457383197,
+                                                            "self": 43.003067206125706,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 152.78894597152248,
-                                                                    "count": 1120936,
+                                                                    "total": 316.37285775109194,
+                                                                    "count": 2346744,
                                                                     "is_parallel": true,
-                                                                    "self": 152.78894597152248
+                                                                    "self": 316.37285775109194
                                                                 }
                                                             }
                                                         }
@@ -421,31 +421,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 2338.514704469766,
-                            "count": 140117,
-                            "self": 10.135464723221958,
+                            "total": 5043.9250766024925,
+                            "count": 293343,
+                            "self": 21.523645554785617,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 436.0033031643834,
-                                    "count": 140117,
-                                    "self": 435.12472358031664,
+                                    "total": 904.3599593398394,
+                                    "count": 293343,
+                                    "self": 902.9554516706849,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.8785795840667561,
-                                            "count": 5,
-                                            "self": 0.8785795840667561
+                                            "total": 1.4045076691545546,
+                                            "count": 8,
+                                            "self": 1.4045076691545546
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 1892.3759365821606,
-                                    "count": 13,
-                                    "self": 187.99826970574213,
+                                    "total": 4118.0414717078675,
+                                    "count": 29,
+                                    "self": 406.04630408110097,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 1704.3776668764185,
-                                            "count": 156,
-                                            "self": 1704.3776668764185
+                                            "total": 3711.9951676267665,
+                                            "count": 348,
+                                            "self": 3711.9951676267665
                                         }
                                     }
                                 }
@@ -454,19 +454,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 4.159519448876381e-07,
+                    "total": 6.25033862888813e-07,
                     "count": 1,
-                    "self": 4.159519448876381e-07
+                    "self": 6.25033862888813e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.132996209023986,
+                    "total": 0.23311050003394485,
                     "count": 1,
-                    "self": 0.004118792014196515,
+                    "self": 0.003456125035881996,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.1288774170097895,
+                            "total": 0.22965437499806285,
                             "count": 1,
-                            "self": 0.1288774170097895
+                            "self": 0.22965437499806285
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,24 +1,24 @@
 {
     "SoccerTwos": {
-        "elo": 271.2064667443272,
+        "elo": 194.71621589386035,
         "checkpoints": [
             {
-                "steps": 80000070,
-                "file_path": "results/sept-run-01/SoccerTwos/SoccerTwos-80000070.onnx",
+                "steps": 116482066,
+                "file_path": "results/sept-run-01/SoccerTwos/SoccerTwos-116482066.onnx",
                 "reward": 0.0,
-                "creation_time": 1725986627.517882,
+                "creation_time": 1726260795.235209,
                 "auxillary_file_paths": [
-                    "results/sept-run-01/SoccerTwos/SoccerTwos-80000070.pt"
+                    "results/sept-run-01/SoccerTwos/SoccerTwos-116482066.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 80000070,
+            "steps": 116482066,
             "file_path": "results/sept-run-01/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1725986627.517882,
+            "creation_time": 1726260795.235209,
             "auxillary_file_paths": [
-                "results/sept-run-01/SoccerTwos/SoccerTwos-80000070.pt"
+                "results/sept-run-01/SoccerTwos/SoccerTwos-116482066.pt"
             ]
         }
     },