20th Push

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f261768320c964ea38a666e212e93438b4d92b8accad81f54af79e5f6655396
+oid sha256:78f977c50b1c06932b41e0682c26e7c6bcdb983b4a14e29bb811d0b906cb3549
 size 2351062

SoccerTwos/SoccerTwos-126999998.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1292e56976df2ca5c07dd7e77212931d364c1cb9e3ac2908131eb4cf014e804d
+size 2351062

SoccerTwos/SoccerTwos-126999998.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:125560c63aee572eb0742b320e60c283dd2314bdab50e87413539e708a0ec986
+size 36303358

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec134a06984c01628bd71b88365f672637f8440c7d108fdc05c0350c655b6062
+oid sha256:f039352616289da615097520d58a69402f5ac0851da7cb3fd3a6ac91c0bf5f84
 size 36301318

SoccerTwos/events.out.tfevents.1726694323.Bretts-MBP.home.5690.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70ddd68e6b82268cf7444637d7d9fbf6863cbb9c26e38322928a01e4530c2f5d
+size 2396707

SoccerTwos/events.out.tfevents.1726703874.Bretts-MBP.home.24914.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b35eab9a028992c0773201c6a40d558ff29d2af17c642209a59ca090a1726a44
+size 1899

SoccerTwos/events.out.tfevents.1726748864.Bretts-MacBook-Pro.local.53210.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66ffddffd7a144232a46057d5c3bf3b948ed8c842292d5f48f0d224fe39720e7
+size 623851

SoccerTwos/events.out.tfevents.1726760366.Bretts-MacBook-Pro.local.51947.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3bd50ddbdb5b873ac250e1536f4db0abdcd64967ff1a9e6945b3076826c2807
+size 771589

SoccerTwos/events.out.tfevents.1726768788.Bretts-MBP.home.45043.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be2cd16d8b7364d899b5a2c287ff74a4e67df8fc028c804a7bb55b36e9438816
+size 7366145

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": 0.999, "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}
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 40960, "buffer_size": 163840, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.3, "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": 0.5, "strength": 0.2, "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": 0.5, "strength": 0.2, "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": 500000, "team_change": 10000, "swap_steps": 500, "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}

configuration.yaml

@@ -6,8 +6,8 @@ behaviors:
       batch_size: 40960
       buffer_size: 163840
       learning_rate: 0.0003
-      beta: 0.01
-      epsilon: 0.2
+      beta: 0.005
+      epsilon: 0.3
       lambd: 0.9
       num_epoch: 3
       learning_rate_schedule: constant
@@ -37,8 +37,8 @@ behaviors:
           goal_conditioning_type: hyper
           deterministic: false
       curiosity:
-        gamma: 0.9
-        strength: 1.0e-06
+        gamma: 0.5
+        strength: 0.2
         network_settings:
           normalize: false
           hidden_units: 512
@@ -50,8 +50,8 @@ behaviors:
         learning_rate: 0.0003
         encoding_size: 512
       rnd:
-        gamma: 0.9
-        strength: 1.0e-06
+        gamma: 0.5
+        strength: 0.2
         network_settings:
           normalize: false
           hidden_units: 128
@@ -70,11 +70,11 @@ behaviors:
     summary_freq: 10000
     threaded: false
     self_play:
-      save_steps: 100000
-      team_change: 400000
-      swap_steps: 2000
+      save_steps: 500000
+      team_change: 10000
+      swap_steps: 500
       window: 30
-      play_against_latest_model_ratio: 0.9
+      play_against_latest_model_ratio: 0.5
       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  0.048 seconds
+- Completed reload, in  0.053 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)
@@ -35,285 +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: 0.352792 ms
+UnloadTime: 0.244708 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": 2.413952589035034,
-            "min": 2.355649948120117,
-            "max": 2.436649799346924,
-            "count": 428
+            "value": 2.255478620529175,
+            "min": 2.230623483657837,
+            "max": 2.276839017868042,
+            "count": 73
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 48742.53125,
-            "min": 40293.83203125,
-            "max": 57293.578125,
-            "count": 428
+            "value": 48357.4609375,
+            "min": 32327.259765625,
+            "max": 53696.97265625,
+            "count": 73
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 72.26470588235294,
-            "min": 50.597938144329895,
-            "max": 96.53846153846153,
-            "count": 428
+            "value": 62.35,
+            "min": 50.5360824742268,
+            "max": 73.58208955223881,
+            "count": 73
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19656.0,
-            "min": 17320.0,
-            "max": 20940.0,
-            "count": 428
+            "value": 19952.0,
+            "min": 12480.0,
+            "max": 20628.0,
+            "count": 73
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 200.5846644937817,
-            "min": 200.5846644937817,
-            "max": 255.10006908123884,
-            "count": 428
+            "value": 200.00727787930185,
+            "min": 160.59296511354657,
+            "max": 203.92215340488602,
+            "count": 73
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 27279.514371154313,
-            "min": 22310.68126471372,
-            "max": 45997.356734281755,
-            "count": 428
+            "value": 32001.1644606883,
+            "min": 18902.286914257813,
+            "max": 35633.72897126356,
+            "count": 73
         },
         "SoccerTwos.Step.mean": {
-            "value": 116479979.0,
-            "min": 112209978.0,
-            "max": 116479979.0,
-            "count": 428
+            "value": 120069898.0,
+            "min": 119349896.0,
+            "max": 120069898.0,
+            "count": 73
         },
         "SoccerTwos.Step.sum": {
-            "value": 116479979.0,
-            "min": 112209978.0,
-            "max": 116479979.0,
-            "count": 428
+            "value": 120069898.0,
+            "min": 119349896.0,
+            "max": 120069898.0,
+            "count": 73
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": -0.18372218310832977,
-            "min": -0.19437754154205322,
-            "max": 0.12453540414571762,
-            "count": 428
+            "value": -0.1278150975704193,
+            "min": -0.170237734913826,
+            "max": 0.08623138070106506,
+            "count": 73
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": -25.169939041137695,
-            "min": -34.03402328491211,
-            "max": 19.427522659301758,
-            "count": 428
+            "value": -20.322601318359375,
+            "min": -24.869155883789062,
+            "max": 14.400640487670898,
+            "count": 73
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.18120113015174866,
-            "min": -0.19503891468048096,
-            "max": 0.12437755614519119,
-            "count": 428
+            "value": -0.1259104162454605,
+            "min": -0.16831789910793304,
+            "max": 0.08471225947141647,
+            "count": 73
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -24.824554443359375,
-            "min": -33.5821647644043,
-            "max": 19.29033851623535,
-            "count": 428
+            "value": -20.019756317138672,
+            "min": -25.439720153808594,
+            "max": 14.146947860717773,
+            "count": 73
         },
         "SoccerTwos.Policy.CuriosityBaselineEstimate.mean": {
-            "value": 0.00013197257067076862,
-            "min": -4.9894701078301296e-05,
-            "max": 0.00027073908131569624,
-            "count": 428
+            "value": 0.02077561430633068,
+            "min": 0.008352533914148808,
+            "max": 0.02189120277762413,
+            "count": 73
         },
         "SoccerTwos.Policy.CuriosityBaselineEstimate.sum": {
-            "value": 0.018080241978168488,
-            "min": -0.007733678445219994,
-            "max": 0.04207998514175415,
-            "count": 428
+            "value": 3.3033227920532227,
+            "min": 1.1812084913253784,
+            "max": 3.915364980697632,
+            "count": 73
         },
         "SoccerTwos.Policy.CuriosityValueEstimate.mean": {
-            "value": 0.0001415555307175964,
-            "min": -5.4355001338990405e-05,
-            "max": 0.0002652776020113379,
-            "count": 428
+            "value": 0.020814398303627968,
+            "min": 0.00840409193187952,
+            "max": 0.0219256691634655,
+            "count": 73
         },
         "SoccerTwos.Policy.CuriosityValueEstimate.sum": {
-            "value": 0.019393106922507286,
-            "min": -0.008425025269389153,
-            "max": 0.04132426530122757,
-            "count": 428
+            "value": 3.3094892501831055,
+            "min": 1.1851625442504883,
+            "max": 3.9218106269836426,
+            "count": 73
         },
         "SoccerTwos.Policy.RndBaselineEstimate.mean": {
-            "value": 9.664618119131774e-06,
-            "min": -6.639550701947883e-05,
-            "max": 5.97319558437448e-05,
-            "count": 428
+            "value": 0.0068628787994384766,
+            "min": 0.006545525975525379,
+            "max": 0.007221938576549292,
+            "count": 73
         },
         "SoccerTwos.Policy.RndBaselineEstimate.sum": {
-            "value": 0.0013240526895970106,
-            "min": -0.009162579663097858,
-            "max": 0.008302741684019566,
-            "count": 428
+            "value": 1.0911977291107178,
+            "min": 0.6152794361114502,
+            "max": 1.3019368648529053,
+            "count": 73
         },
         "SoccerTwos.Policy.RndValueEstimate.mean": {
-            "value": 1.0724314051913098e-05,
-            "min": -7.216515950858593e-05,
-            "max": 5.9375102864578366e-05,
-            "count": 428
+            "value": 0.006880544126033783,
+            "min": 0.0065576122142374516,
+            "max": 0.007235044613480568,
+            "count": 73
         },
         "SoccerTwos.Policy.RndValueEstimate.sum": {
-            "value": 0.0014692309778183699,
-            "min": -0.009958792477846146,
-            "max": 0.008253139443695545,
-            "count": 428
+            "value": 1.0940065383911133,
+            "min": 0.6164155602455139,
+            "max": 1.3072426319122314,
+            "count": 73
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 428
+            "count": 73
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 428
+            "count": 73
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.30921314058512667,
-            "min": -0.34116986434753627,
-            "max": 0.3086177231390265,
-            "count": 428
+            "value": -0.14068931003786483,
+            "min": -0.25714838889337355,
+            "max": 0.2380424672610139,
+            "count": 73
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -42.36220026016235,
-            "min": -49.810800194740295,
-            "max": 48.76160025596619,
-            "count": 428
+            "value": -22.369600296020508,
+            "min": -39.98679995536804,
+            "max": 34.75420022010803,
+            "count": 73
         },
         "SoccerTwos.Policy.CuriosityReward.mean": {
-            "value": 2.8015310108358346e-06,
+            "value": 0.549969781143298,
             "min": 0.0,
-            "max": 7.618662638938426e-06,
-            "count": 428
+            "max": 0.9045167695183087,
+            "count": 73
         },
         "SoccerTwos.Policy.CuriosityReward.sum": {
-            "value": 0.00038380974848450933,
+            "value": 87.44519520178437,
             "min": 0.0,
-            "max": 0.0010100169779150292,
-            "count": 428
+            "max": 125.58684200793505,
+            "count": 73
         },
         "SoccerTwos.Policy.RndReward.mean": {
-            "value": 1.3432801519607946e-06,
-            "min": 8.947482167043677e-07,
-            "max": 1.7273090733738172e-06,
-            "count": 428
+            "value": 0.220354071941297,
+            "min": 0.1871111254860676,
+            "max": 0.27255435835625696,
+            "count": 73
         },
         "SoccerTwos.Policy.RndReward.sum": {
-            "value": 0.00018402938081862885,
-            "min": 0.00015929336030495733,
-            "max": 0.00019037561346024745,
-            "count": 428
+            "value": 35.036297438666224,
+            "min": 20.47128874901682,
+            "max": 37.64491491857916,
+            "count": 73
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.30921314058512667,
-            "min": -0.34116986434753627,
-            "max": 0.3086177231390265,
-            "count": 428
+            "value": -0.14068931003786483,
+            "min": -0.25714838889337355,
+            "max": 0.2380424672610139,
+            "count": 73
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -42.36220026016235,
-            "min": -49.810800194740295,
-            "max": 48.76160025596619,
-            "count": 428
+            "value": -22.369600296020508,
+            "min": -39.98679995536804,
+            "max": 34.75420022010803,
+            "count": 73
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 428
+            "count": 73
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 428
+            "count": 73
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.010974738972436171,
-            "min": 0.006480928104186508,
-            "max": 0.017731858902455617,
-            "count": 28
+            "value": 0.013634561997605488,
+            "min": 0.00939689805575957,
+            "max": 0.017807006215055782,
+            "count": 4
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.010974738972436171,
-            "min": 0.006480928104186508,
-            "max": 0.017731858902455617,
-            "count": 28
+            "value": 0.013634561997605488,
+            "min": 0.00939689805575957,
+            "max": 0.017807006215055782,
+            "count": 4
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.01760079540933172,
-            "min": 0.017158242408186197,
-            "max": 0.020099001626173656,
-            "count": 28
+            "value": 0.019645538957168657,
+            "min": 0.019196889828890562,
+            "max": 0.019724952677885692,
+            "count": 4
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.01760079540933172,
-            "min": 0.017158242408186197,
-            "max": 0.020099001626173656,
-            "count": 28
+            "value": 0.019645538957168657,
+            "min": 0.019196889828890562,
+            "max": 0.019724952677885692,
+            "count": 4
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.01818520234276851,
-            "min": 0.017673577802876633,
-            "max": 0.02067598778133591,
-            "count": 28
+            "value": 0.02021182266374429,
+            "min": 0.01983766940732797,
+            "max": 0.02021182266374429,
+            "count": 4
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.01818520234276851,
-            "min": 0.017673577802876633,
-            "max": 0.02067598778133591,
-            "count": 28
+            "value": 0.02021182266374429,
+            "min": 0.01983766940732797,
+            "max": 0.02021182266374429,
+            "count": 4
         },
         "SoccerTwos.Policy.LearningRate.mean": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 28
+            "count": 4
         },
         "SoccerTwos.Policy.LearningRate.sum": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 28
+            "count": 4
         },
         "SoccerTwos.Policy.Epsilon.mean": {
-            "value": 0.20000000000000004,
-            "min": 0.20000000000000004,
-            "max": 0.20000000000000004,
-            "count": 28
+            "value": 0.29999999999999993,
+            "min": 0.29999999999999993,
+            "max": 0.29999999999999993,
+            "count": 4
         },
         "SoccerTwos.Policy.Epsilon.sum": {
-            "value": 0.20000000000000004,
-            "min": 0.20000000000000004,
-            "max": 0.20000000000000004,
-            "count": 28
+            "value": 0.29999999999999993,
+            "min": 0.29999999999999993,
+            "max": 0.29999999999999993,
+            "count": 4
         },
         "SoccerTwos.Policy.Beta.mean": {
-            "value": 0.009883782196138,
-            "min": 0.009883782196138,
-            "max": 0.009887763606742,
-            "count": 28
+            "value": 0.004940154883094001,
+            "min": 0.004940154883094001,
+            "max": 0.004940374242496,
+            "count": 4
         },
         "SoccerTwos.Policy.Beta.sum": {
-            "value": 0.009883782196138,
-            "min": 0.009883782196138,
-            "max": 0.009887763606742,
-            "count": 28
+            "value": 0.004940154883094001,
+            "min": 0.004940154883094001,
+            "max": 0.004940374242496,
+            "count": 4
         },
         "SoccerTwos.Losses.CuriosityForwardLoss.mean": {
-            "value": 0.03778785094618797,
-            "min": 0.03734184770534436,
-            "max": 0.1971647860482335,
-            "count": 28
+            "value": 0.04491656149427096,
+            "min": 0.04491656149427096,
+            "max": 0.09600517495224874,
+            "count": 4
         },
         "SoccerTwos.Losses.CuriosityForwardLoss.sum": {
-            "value": 0.03778785094618797,
-            "min": 0.03734184770534436,
-            "max": 0.1971647860482335,
-            "count": 28
+            "value": 0.04491656149427096,
+            "min": 0.04491656149427096,
+            "max": 0.09600517495224874,
+            "count": 4
         },
         "SoccerTwos.Losses.CuriosityInverseLoss.mean": {
-            "value": 1.6315673093001049,
-            "min": 1.6234056651592255,
-            "max": 2.092972139517466,
-            "count": 28
+            "value": 1.5401246945063274,
+            "min": 1.5401246945063274,
+            "max": 1.7537684241930644,
+            "count": 4
         },
         "SoccerTwos.Losses.CuriosityInverseLoss.sum": {
-            "value": 1.6315673093001049,
-            "min": 1.6234056651592255,
-            "max": 2.092972139517466,
-            "count": 28
+            "value": 1.5401246945063274,
+            "min": 1.5401246945063274,
+            "max": 1.7537684241930644,
+            "count": 4
         },
         "SoccerTwos.Losses.RNDLoss.mean": {
-            "value": 0.015613269060850143,
-            "min": 0.015565264038741589,
-            "max": 0.017592713236808777,
-            "count": 28
+            "value": 0.01586015336215496,
+            "min": 0.01586015336215496,
+            "max": 0.017172401770949364,
+            "count": 4
         },
         "SoccerTwos.Losses.RNDLoss.sum": {
-            "value": 0.015613269060850143,
-            "min": 0.015565264038741589,
-            "max": 0.017592713236808777,
-            "count": 28
+            "value": 0.01586015336215496,
+            "min": 0.01586015336215496,
+            "max": 0.017172401770949364,
+            "count": 4
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1726243068",
+        "start_time_seconds": "1726760363",
         "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": "1726260795"
+        "end_time_seconds": "1726763505"
     },
-    "total": 16904.79020066606,
+    "total": 3141.775703000021,
     "count": 1,
-    "self": 0.167630082112737,
+    "self": 0.019297625054605305,
     "children": {
         "run_training.setup": {
-            "total": 0.023219667025841773,
+            "total": 0.019264457980170846,
             "count": 1,
-            "self": 0.023219667025841773
+            "self": 0.019264457980170846
         },
         "TrainerController.start_learning": {
-            "total": 16904.59935091692,
+            "total": 3141.7371409169864,
             "count": 1,
-            "self": 2.453233522363007,
+            "self": 0.616179323522374,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.8081024570856243,
-                    "count": 12,
-                    "self": 3.8081024570856243
+                    "total": 6.17303312709555,
+                    "count": 74,
+                    "self": 6.17303312709555
                 },
                 "TrainerController.advance": {
-                    "total": 16898.104903812404,
-                    "count": 293343,
-                    "self": 2.2329050848493353,
+                    "total": 3134.5881778413896,
+                    "count": 54375,
+                    "self": 0.46005123551003635,
                     "children": {
                         "env_step": {
-                            "total": 11851.946922125062,
-                            "count": 293343,
-                            "self": 11464.108450845582,
+                            "total": 2235.4445955763804,
+                            "count": 54375,
+                            "self": 2155.006646992173,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 386.3168923628982,
-                                    "count": 293343,
-                                    "self": 15.735434583271854,
+                                    "total": 80.10751251596957,
+                                    "count": 54375,
+                                    "self": 3.1288182924035937,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 370.58145777962636,
-                                            "count": 536174,
-                                            "self": 370.58145777962636
+                                            "total": 76.97869422356598,
+                                            "count": 99600,
+                                            "self": 76.97869422356598
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 1.5215789165813476,
-                                    "count": 293343,
+                                    "total": 0.3304360682377592,
+                                    "count": 54375,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 16897.44152066519,
-                                            "count": 293343,
+                                            "total": 3000.0345093504293,
+                                            "count": 54375,
                                             "is_parallel": true,
-                                            "self": 5736.2697331981035,
+                                            "self": 905.6446920702001,
                                             "children": {
                                                 "steps_from_proto": {
-                                                    "total": 0.016120707150548697,
-                                                    "count": 24,
+                                                    "total": 0.1013583323219791,
+                                                    "count": 148,
                                                     "is_parallel": true,
-                                                    "self": 0.0021714119939133525,
+                                                    "self": 0.013186299125663936,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.013949295156635344,
-                                                            "count": 96,
+                                                            "total": 0.08817203319631517,
+                                                            "count": 592,
                                                             "is_parallel": true,
-                                                            "self": 0.013949295156635344
+                                                            "self": 0.08817203319631517
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 11161.155666759936,
-                                                    "count": 293343,
+                                                    "total": 2094.288458947907,
+                                                    "count": 54375,
                                                     "is_parallel": true,
-                                                    "self": 28.08294066612143,
+                                                    "self": 5.375599776511081,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 219.95445196295623,
-                                                            "count": 293343,
+                                                            "total": 41.997091523138806,
+                                                            "count": 54375,
                                                             "is_parallel": true,
-                                                            "self": 219.95445196295623
+                                                            "self": 41.997091523138806
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 10553.74234917364,
-                                                            "count": 293343,
+                                                            "total": 1978.6759033377748,
+                                                            "count": 54375,
                                                             "is_parallel": true,
-                                                            "self": 10553.74234917364
+                                                            "self": 1978.6759033377748
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 359.37592495721765,
-                                                            "count": 586686,
+                                                            "total": 68.23986431048252,
+                                                            "count": 108750,
                                                             "is_parallel": true,
-                                                            "self": 43.003067206125706,
+                                                            "self": 8.25137705472298,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 316.37285775109194,
-                                                                    "count": 2346744,
+                                                                    "total": 59.98848725575954,
+                                                                    "count": 435000,
                                                                     "is_parallel": true,
-                                                                    "self": 316.37285775109194
+                                                                    "self": 59.98848725575954
                                                                 }
                                                             }
                                                         }
@@ -421,31 +421,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 5043.9250766024925,
-                            "count": 293343,
-                            "self": 21.523645554785617,
+                            "total": 898.6835310294991,
+                            "count": 54375,
+                            "self": 5.210828961106017,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 904.3599593398394,
-                                    "count": 293343,
-                                    "self": 902.9554516706849,
+                                    "total": 163.99640706938226,
+                                    "count": 54375,
+                                    "self": 163.62267173535656,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 1.4045076691545546,
-                                            "count": 8,
-                                            "self": 1.4045076691545546
+                                            "total": 0.3737353340256959,
+                                            "count": 2,
+                                            "self": 0.3737353340256959
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 4118.0414717078675,
-                                    "count": 29,
-                                    "self": 406.04630408110097,
+                                    "total": 729.4762949990109,
+                                    "count": 5,
+                                    "self": 71.07644628593698,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 3711.9951676267665,
-                                            "count": 348,
-                                            "self": 3711.9951676267665
+                                            "total": 658.3998487130739,
+                                            "count": 59,
+                                            "self": 658.3998487130739
                                         }
                                     }
                                 }
@@ -454,19 +454,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 6.25033862888813e-07,
+                    "total": 8.749775588512421e-07,
                     "count": 1,
-                    "self": 6.25033862888813e-07
+                    "self": 8.749775588512421e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.23311050003394485,
+                    "total": 0.359749750001356,
                     "count": 1,
-                    "self": 0.003456125035881996,
+                    "self": 0.007718999986536801,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.22965437499806285,
+                            "total": 0.3520307500148192,
                             "count": 1,
-                            "self": 0.22965437499806285
+                            "self": 0.3520307500148192
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,24 +1,24 @@
 {
     "SoccerTwos": {
-        "elo": 194.71621589386035,
+        "elo": 187.00288389830894,
         "checkpoints": [
             {
-                "steps": 116482066,
-                "file_path": "results/sept-run-01/SoccerTwos/SoccerTwos-116482066.onnx",
-                "reward": 0.0,
-                "creation_time": 1726260795.235209,
+                "steps": 120077520,
+                "file_path": "results/sept-run-01/SoccerTwos/SoccerTwos-120077520.onnx",
+                "reward": null,
+                "creation_time": 1726763505.4426508,
                 "auxillary_file_paths": [
-                    "results/sept-run-01/SoccerTwos/SoccerTwos-116482066.pt"
+                    "results/sept-run-01/SoccerTwos/SoccerTwos-120077520.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 116482066,
+            "steps": 120077520,
             "file_path": "results/sept-run-01/SoccerTwos.onnx",
-            "reward": 0.0,
-            "creation_time": 1726260795.235209,
+            "reward": null,
+            "creation_time": 1726763505.4426508,
             "auxillary_file_paths": [
-                "results/sept-run-01/SoccerTwos/SoccerTwos-116482066.pt"
+                "results/sept-run-01/SoccerTwos/SoccerTwos-120077520.pt"
             ]
         }
     },