24th Push

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc1624457677003f906d6d873309e454d7ad3aa270fc751316783c2ecb593bd3
+oid sha256:b6442ff347a0a397026b2704653f38adc0a1180db5f9352f0a9d4b6b3e992f39
 size 2351062

SoccerTwos/SoccerTwos-189129132.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6442ff347a0a397026b2704653f38adc0a1180db5f9352f0a9d4b6b3e992f39
+size 2351062

SoccerTwos/SoccerTwos-189129132.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c0c1bb302a1b8a88d2a9d83092570dff9380a6cc50f84d2b057d63cadbb9b70
+size 36303358

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87b4e90826f5ad5b303263f4481783b3aa9fd1dcfe999458a3d2bb6e2e8ddcce
+oid sha256:7a6696363a52b828313de242e60fd218cacf6d1151c38d43e8a75b685c961ffa
 size 36301318

SoccerTwos/events.out.tfevents.1727126120.Bretts-MacBook-Pro.local.36468.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03a3a5569488803ebc6616b59aba4e9a5e85f618015802753eb18a4d26a98bf6
-size 1003444
+oid sha256:e1b41f251162f054edcaeded7f932b832094126503abf993fd4385be5b3966c0
+size 1013958

SoccerTwos/events.out.tfevents.1727188532.Bretts-MBP.home.93120.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8787932c87ca78b67da071f81bfd55eb3c0864edfc89a247154ec946aec3912d
+size 11433805

SoccerTwos/events.out.tfevents.1727224624.Bretts-MBP.home.16631.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec834c7d75e81e1025bd555cde6b22f5ce49973368732eedab6125bb238f5ac4
+size 12417

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 60000, "buffer_size": 180000, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "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": 0.7, "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": 0.7, "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": 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}
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2000, "buffer_size": 8000, "learning_rate": 0.0003, "beta": 0.0, "epsilon": 0.2, "lambd": 0.99, "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": 0.7, "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": 0.7, "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

@@ -3,12 +3,12 @@ behaviors:
   SoccerTwos:
     trainer_type: poca
     hyperparameters:
-      batch_size: 60000
-      buffer_size: 180000
+      batch_size: 2000
+      buffer_size: 8000
       learning_rate: 0.0003
-      beta: 0.005
+      beta: 0.0
       epsilon: 0.2
-      lambd: 0.95
+      lambd: 0.99
       num_epoch: 3
       learning_rate_schedule: constant
       beta_schedule: linear
@@ -70,11 +70,11 @@ behaviors:
     summary_freq: 10000
     threaded: false
     self_play:
-      save_steps: 500000
-      team_change: 10000
-      swap_steps: 500
+      save_steps: 100000
+      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  0.047 seconds
+- Completed reload, in  0.044 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 +35,6 @@ 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: 0.217250 ms
+UnloadTime: 0.270125 ms
 Registered Communicator in Agent.
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
-GRPC Exception: Status(StatusCode=Unknown, Detail="Exception calling application: [Errno 32] Broken pipe"). Disconnecting from trainer.
-Thread 0x16f2e7000 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]: 19455 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 0.7 KB
-      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 B
-      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 4
-    [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]: 19456 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]: 19456 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]: 19455 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]: 19456 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]: 19456 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]: 19455 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]: 19456 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]: 19455 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": 1.7164949178695679,
-            "min": 1.6976535320281982,
-            "max": 1.7401092052459717,
-            "count": 96
+            "value": 1.3781930208206177,
+            "min": 1.3744720220565796,
+            "max": 1.741039514541626,
+            "count": 1034
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 38010.0625,
-            "min": 26713.73828125,
-            "max": 42950.8359375,
-            "count": 96
+            "value": 28534.109375,
+            "min": 24589.529296875,
+            "max": 40743.671875,
+            "count": 1034
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 49.81818181818182,
-            "min": 49.81818181818182,
-            "max": 89.5,
-            "count": 96
+            "value": 79.45161290322581,
+            "min": 49.166666666666664,
+            "max": 119.3170731707317,
+            "count": 1034
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19728.0,
-            "min": 12944.0,
-            "max": 20852.0,
-            "count": 96
+            "value": 19704.0,
+            "min": 16560.0,
+            "max": 21436.0,
+            "count": 1034
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 185.99996018676066,
-            "min": 176.49177442883757,
-            "max": 225.37289222574412,
-            "count": 96
+            "value": 93.65101164083741,
+            "min": 86.56045520432379,
+            "max": 184.57299554666258,
+            "count": 1034
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 36827.99211697861,
-            "min": 17680.353353375765,
-            "max": 41919.35795398841,
-            "count": 96
+            "value": 11612.725443463838,
+            "min": 8691.930092205928,
+            "max": 29498.735260938094,
+            "count": 1034
         },
         "SoccerTwos.Step.mean": {
-            "value": 178779942.0,
-            "min": 177829990.0,
-            "max": 178779942.0,
-            "count": 96
+            "value": 189119996.0,
+            "min": 178789949.0,
+            "max": 189119996.0,
+            "count": 1034
         },
         "SoccerTwos.Step.sum": {
-            "value": 178779942.0,
-            "min": 177829990.0,
-            "max": 178779942.0,
-            "count": 96
+            "value": 189119996.0,
+            "min": 178789949.0,
+            "max": 189119996.0,
+            "count": 1034
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": -0.0839383602142334,
-            "min": -0.1227869987487793,
-            "max": 0.1261693239212036,
-            "count": 96
+            "value": -0.07243078202009201,
+            "min": -0.3360375463962555,
+            "max": 0.18055570125579834,
+            "count": 1034
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": -16.535856246948242,
-            "min": -20.75100326538086,
-            "max": 20.33123779296875,
-            "count": 96
+            "value": -8.981416702270508,
+            "min": -53.181800842285156,
+            "max": 24.610076904296875,
+            "count": 1034
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.060450199991464615,
-            "min": -0.10872241854667664,
-            "max": 0.138449028134346,
-            "count": 96
+            "value": -0.07893384248018265,
+            "min": -0.3407939374446869,
+            "max": 0.17904900014400482,
+            "count": 1034
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -11.908689498901367,
-            "min": -18.3893985748291,
-            "max": 21.74520492553711,
-            "count": 96
+            "value": -9.787796020507812,
+            "min": -54.62144470214844,
+            "max": 23.522796630859375,
+            "count": 1034
         },
         "SoccerTwos.Policy.CuriosityBaselineEstimate.mean": {
-            "value": 0.007995746098458767,
-            "min": -0.002932249801233411,
-            "max": 0.008009606041014194,
-            "count": 96
+            "value": 1.9122660432913108e-07,
+            "min": -0.001151102944277227,
+            "max": 0.0024182319175451994,
+            "count": 1034
         },
         "SoccerTwos.Policy.CuriosityBaselineEstimate.sum": {
-            "value": 1.5751619338989258,
-            "min": -0.5018134713172913,
-            "max": 1.5751619338989258,
-            "count": 96
+            "value": 2.3712098482064903e-05,
+            "min": -0.16115440428256989,
+            "max": 0.34580716490745544,
+            "count": 1034
         },
         "SoccerTwos.Policy.CuriosityValueEstimate.mean": {
-            "value": -0.0001023145523504354,
-            "min": -0.002700324635952711,
-            "max": 0.0007662046700716019,
-            "count": 96
+            "value": 1.9236215109685872e-07,
+            "min": -0.0011043738340958953,
+            "max": 0.0020429561845958233,
+            "count": 1034
         },
         "SoccerTwos.Policy.CuriosityValueEstimate.sum": {
-            "value": -0.02015596628189087,
-            "min": -0.5100942850112915,
-            "max": 0.1199265718460083,
-            "count": 96
+            "value": 2.3852906451793388e-05,
+            "min": -0.15461233258247375,
+            "max": 0.29435789585113525,
+            "count": 1034
         },
         "SoccerTwos.Policy.RndBaselineEstimate.mean": {
-            "value": 0.008453146554529667,
-            "min": -4.742640521726571e-05,
-            "max": 0.008468522690236568,
-            "count": 96
+            "value": 2.2311963832066795e-08,
+            "min": -0.002267050789669156,
+            "max": 0.002958990866318345,
+            "count": 1034
         },
         "SoccerTwos.Policy.RndBaselineEstimate.sum": {
-            "value": 1.6652698516845703,
-            "min": -0.007777930237352848,
-            "max": 1.6652698516845703,
-            "count": 96
+            "value": 2.766683564914274e-06,
+            "min": -0.3445917069911957,
+            "max": 0.4231356978416443,
+            "count": 1034
         },
         "SoccerTwos.Policy.RndValueEstimate.mean": {
-            "value": 5.468887684401125e-05,
-            "min": -5.1568593335105106e-05,
-            "max": 0.0018458361737430096,
-            "count": 96
+            "value": 2.1164218821922987e-08,
+            "min": -0.0025371587835252285,
+            "max": 0.0022697285749018192,
+            "count": 1034
         },
         "SoccerTwos.Policy.RndValueEstimate.sum": {
-            "value": 0.010773709043860435,
-            "min": -0.008457249030470848,
-            "max": 0.16612525284290314,
-            "count": 96
+            "value": 2.624363105496741e-06,
+            "min": -0.33674874901771545,
+            "max": 0.3245711922645569,
+            "count": 1034
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 96
+            "count": 1034
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 96
+            "count": 1034
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.012483251276355104,
-            "min": -0.3036496898402338,
-            "max": 0.21833706318915308,
-            "count": 96
+            "value": -0.021679032233453566,
+            "min": -0.44282786865703394,
+            "max": 0.390961290367188,
+            "count": 1034
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -2.4592005014419556,
-            "min": -48.88760006427765,
-            "max": 38.85360026359558,
-            "count": 96
+            "value": -2.688199996948242,
+            "min": -57.01079988479614,
+            "max": 48.47920000553131,
+            "count": 1034
         },
         "SoccerTwos.Policy.CuriosityReward.mean": {
-            "value": 2.6298247309723637e-06,
-            "min": 0.0,
-            "max": 5.810932576475982e-06,
-            "count": 96
+            "value": 4.86458082303531e-06,
+            "min": 5.443049713948268e-07,
+            "max": 6.574109662139293e-06,
+            "count": 1034
         },
         "SoccerTwos.Policy.CuriosityReward.sum": {
-            "value": 0.0005180754720015557,
-            "min": 0.0,
-            "max": 0.0007590712531353461,
-            "count": 96
+            "value": 0.0006032080220563785,
+            "min": 7.783561090946023e-05,
+            "max": 0.000689425590422843,
+            "count": 1034
         },
         "SoccerTwos.Policy.RndReward.mean": {
-            "value": 8.549423112740667e-07,
-            "min": 8.549423112740667e-07,
-            "max": 1.6037936830513843e-06,
-            "count": 96
+            "value": 1.287715538959978e-06,
+            "min": 7.856230547035695e-07,
+            "max": 2.1249771742280145e-06,
+            "count": 1034
         },
         "SoccerTwos.Policy.RndReward.sum": {
-            "value": 0.00016842363532099114,
-            "min": 0.000107408565327205,
-            "max": 0.00019332374388270068,
-            "count": 96
+            "value": 0.00015967672683103729,
+            "min": 0.00014387621671119177,
+            "max": 0.00018277378640618736,
+            "count": 1034
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.012483251276355104,
-            "min": -0.3036496898402338,
-            "max": 0.21833706318915308,
-            "count": 96
+            "value": -0.021679032233453566,
+            "min": -0.44282786865703394,
+            "max": 0.390961290367188,
+            "count": 1034
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -2.4592005014419556,
-            "min": -48.88760006427765,
-            "max": 38.85360026359558,
-            "count": 96
-        },
-        "SoccerTwos.IsTraining.mean": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 96
-        },
-        "SoccerTwos.IsTraining.sum": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 96
+            "value": -2.688199996948242,
+            "min": -57.01079988479614,
+            "max": 48.47920000553131,
+            "count": 1034
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.011109193373057578,
-            "min": 0.009515493228617642,
-            "max": 0.015159902214590047,
-            "count": 5
+            "value": 0.047321543184807524,
+            "min": 0.03148699582864841,
+            "max": 0.11992886561589937,
+            "count": 1034
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.011109193373057578,
-            "min": 0.009515493228617642,
-            "max": 0.015159902214590047,
-            "count": 5
+            "value": 0.047321543184807524,
+            "min": 0.03148699582864841,
+            "max": 0.1902564300495821,
+            "count": 1034
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.04075721361570888,
-            "min": 0.04075721361570888,
-            "max": 0.04227158096101549,
-            "count": 5
+            "value": 0.11854892037808895,
+            "min": 0.07656206066409747,
+            "max": 0.1504069591561953,
+            "count": 1034
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.04075721361570888,
-            "min": 0.04075721361570888,
-            "max": 0.04227158096101549,
-            "count": 5
+            "value": 0.11854892037808895,
+            "min": 0.07656206066409747,
+            "max": 0.26776626519858837,
+            "count": 1034
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.04147735031114684,
-            "min": 0.04147735031114684,
-            "max": 0.043164278070131935,
-            "count": 5
+            "value": 0.11993555227915446,
+            "min": 0.07771284443636735,
+            "max": 0.15372675905625025,
+            "count": 1034
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.04147735031114684,
-            "min": 0.04147735031114684,
-            "max": 0.043164278070131935,
-            "count": 5
+            "value": 0.11993555227915446,
+            "min": 0.07771284443636735,
+            "max": 0.27362133065859473,
+            "count": 1034
         },
         "SoccerTwos.Policy.LearningRate.mean": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 5
+            "count": 1034
         },
         "SoccerTwos.Policy.LearningRate.sum": {
             "value": 0.0003,
             "min": 0.0003,
-            "max": 0.0003,
-            "count": 5
+            "max": 0.0006,
+            "count": 1034
         },
         "SoccerTwos.Policy.Epsilon.mean": {
-            "value": 0.2,
-            "min": 0.2,
-            "max": 0.2,
-            "count": 5
+            "value": 0.20000000000000004,
+            "min": 0.20000000000000004,
+            "max": 0.20000000000000004,
+            "count": 1034
         },
         "SoccerTwos.Policy.Epsilon.sum": {
-            "value": 0.2,
-            "min": 0.2,
-            "max": 0.2,
-            "count": 5
+            "value": 0.20000000000000004,
+            "min": 0.20000000000000004,
+            "max": 0.4000000000000001,
+            "count": 1034
         },
         "SoccerTwos.Policy.Beta.mean": {
-            "value": 0.004910863537186,
-            "min": 0.004910863537186,
-            "max": 0.00491118557482,
-            "count": 5
+            "value": 1.8911295400000063e-07,
+            "min": 1.7878892000000035e-07,
+            "max": 1.8911295400000063e-07,
+            "count": 1034
         },
         "SoccerTwos.Policy.Beta.sum": {
-            "value": 0.004910863537186,
-            "min": 0.004910863537186,
-            "max": 0.00491118557482,
-            "count": 5
+            "value": 1.8911295400000063e-07,
+            "min": 1.7878892000000035e-07,
+            "max": 3.781875359999997e-07,
+            "count": 1034
         },
         "SoccerTwos.Losses.CuriosityForwardLoss.mean": {
-            "value": 0.05262338866790136,
-            "min": 0.05262338866790136,
-            "max": 0.09950606235199505,
-            "count": 5
+            "value": 0.059419798043866955,
+            "min": 0.04430011318375667,
+            "max": 0.09529003656158845,
+            "count": 1034
         },
         "SoccerTwos.Losses.CuriosityForwardLoss.sum": {
-            "value": 0.05262338866790136,
-            "min": 0.05262338866790136,
-            "max": 0.09950606235199505,
-            "count": 5
+            "value": 0.059419798043866955,
+            "min": 0.04430011318375667,
+            "max": 0.1239892446125547,
+            "count": 1034
         },
         "SoccerTwos.Losses.CuriosityInverseLoss.mean": {
-            "value": 1.34821445412106,
-            "min": 1.34821445412106,
-            "max": 1.7424639066060383,
-            "count": 5
+            "value": 1.2251605292161305,
+            "min": 1.2107319831848145,
+            "max": 1.6226676205794017,
+            "count": 1034
         },
         "SoccerTwos.Losses.CuriosityInverseLoss.sum": {
-            "value": 1.34821445412106,
-            "min": 1.34821445412106,
-            "max": 1.7424639066060383,
-            "count": 5
+            "value": 1.2251605292161305,
+            "min": 1.2107319831848145,
+            "max": 2.791062255700429,
+            "count": 1034
         },
         "SoccerTwos.Losses.RNDLoss.mean": {
-            "value": 0.015367019921541214,
-            "min": 0.015353260561823845,
-            "max": 0.01684141904115677,
-            "count": 5
+            "value": 0.014285321347415447,
+            "min": 0.012901323847472668,
+            "max": 0.016783548519015312,
+            "count": 1034
         },
         "SoccerTwos.Losses.RNDLoss.sum": {
-            "value": 0.015367019921541214,
-            "min": 0.015353260561823845,
-            "max": 0.01684141904115677,
-            "count": 5
+            "value": 0.014285321347415447,
+            "min": 0.012901323847472668,
+            "max": 0.032633792608976364,
+            "count": 1034
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 1034
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 1034
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1727126117",
+        "start_time_seconds": "1727188528",
         "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": "1727130350"
+        "end_time_seconds": "1727224512"
     },
-    "total": 4232.809460124932,
+    "total": 35983.49770029192,
     "count": 1,
-    "self": 0.22196899983100593,
+    "self": 0.08363945898599923,
     "children": {
         "run_training.setup": {
-            "total": 0.024208958027884364,
+            "total": 0.018821208039298654,
             "count": 1,
-            "self": 0.024208958027884364
+            "self": 0.018821208039298654
         },
         "TrainerController.start_learning": {
-            "total": 4232.563282167073,
+            "total": 35983.39523962489,
             "count": 1,
-            "self": 0.6813796926289797,
+            "self": 6.235370217356831,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 6.979007874848321,
-                    "count": 96,
-                    "self": 6.979007874848321
+                    "total": 4.630654625128955,
+                    "count": 27,
+                    "self": 4.630654625128955
                 },
                 "TrainerController.advance": {
-                    "total": 4224.769748307532,
-                    "count": 70688,
-                    "self": 0.5682495513465255,
+                    "total": 35972.41701407451,
+                    "count": 704312,
+                    "self": 5.832071551587433,
                     "children": {
                         "env_step": {
-                            "total": 2887.7094854547177,
-                            "count": 70688,
-                            "self": 2786.0707781801466,
+                            "total": 28817.246928388486,
+                            "count": 704312,
+                            "self": 27742.76929838606,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 101.23914131778292,
-                                    "count": 70688,
-                                    "self": 4.147173700621352,
+                                    "total": 1070.5935122335795,
+                                    "count": 704312,
+                                    "self": 39.795816264813766,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 97.09196761716157,
-                                            "count": 129750,
-                                            "self": 97.09196761716157
+                                            "total": 1030.7976959687658,
+                                            "count": 1296574,
+                                            "self": 1030.7976959687658
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.39956595678813756,
-                                    "count": 70687,
+                                    "total": 3.8841177688445896,
+                                    "count": 704311,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 4228.456313202158,
-                                            "count": 70687,
+                                            "total": 35970.29673069273,
+                                            "count": 704311,
                                             "is_parallel": true,
-                                            "self": 1518.831769473618,
+                                            "self": 8961.662063932745,
                                             "children": {
                                                 "steps_from_proto": {
-                                                    "total": 0.12777390936389565,
-                                                    "count": 192,
+                                                    "total": 0.03622587467543781,
+                                                    "count": 54,
                                                     "is_parallel": true,
-                                                    "self": 0.01669394364580512,
+                                                    "self": 0.00454957690089941,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.11107996571809053,
-                                                            "count": 768,
+                                                            "total": 0.0316762977745384,
+                                                            "count": 216,
                                                             "is_parallel": true,
-                                                            "self": 0.11107996571809053
+                                                            "self": 0.0316762977745384
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 2709.496769819176,
-                                                    "count": 70687,
+                                                    "total": 27008.59844088531,
+                                                    "count": 704311,
                                                     "is_parallel": true,
-                                                    "self": 7.086204035207629,
+                                                    "self": 70.87291683093645,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 53.40011290227994,
-                                                            "count": 70687,
+                                                            "total": 527.5704898335971,
+                                                            "count": 704311,
                                                             "is_parallel": true,
-                                                            "self": 53.40011290227994
+                                                            "self": 527.5704898335971
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 2561.940888369223,
-                                                            "count": 70687,
+                                                            "total": 25540.6204636693,
+                                                            "count": 704311,
                                                             "is_parallel": true,
-                                                            "self": 2561.940888369223
+                                                            "self": 25540.6204636693
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 87.06956451246515,
-                                                            "count": 141374,
+                                                            "total": 869.5345705514774,
+                                                            "count": 1408622,
                                                             "is_parallel": true,
-                                                            "self": 10.543289387831464,
+                                                            "self": 105.35918086278252,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 76.52627512463368,
-                                                                    "count": 565496,
+                                                                    "total": 764.1753896886948,
+                                                                    "count": 5634488,
                                                                     "is_parallel": true,
-                                                                    "self": 76.52627512463368
+                                                                    "self": 764.1753896886948
                                                                 }
                                                             }
                                                         }
@@ -421,31 +421,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 1336.4920133014675,
-                            "count": 70687,
-                            "self": 5.670989201636985,
+                            "total": 7149.338014134439,
+                            "count": 704311,
+                            "self": 56.82280270801857,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 213.4259012658149,
-                                    "count": 70687,
-                                    "self": 213.13595618261024,
+                                    "total": 2286.966482809512,
+                                    "count": 704311,
+                                    "self": 2284.324856644962,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.28994508320465684,
-                                            "count": 2,
-                                            "self": 0.28994508320465684
+                                            "total": 2.6416261645499617,
+                                            "count": 21,
+                                            "self": 2.6416261645499617
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 1117.3951228340156,
-                                    "count": 5,
-                                    "self": 81.62112637190148,
+                                    "total": 4805.548728616908,
+                                    "count": 1397,
+                                    "self": 923.5975278588012,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 1035.7739964621142,
-                                            "count": 45,
-                                            "self": 1035.7739964621142
+                                            "total": 3881.951200758107,
+                                            "count": 16764,
+                                            "self": 3881.951200758107
                                         }
                                     }
                                 }
@@ -454,19 +454,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 5.420297384262085e-07,
+                    "total": 4.5797787606716156e-07,
                     "count": 1,
-                    "self": 5.420297384262085e-07
+                    "self": 4.5797787606716156e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.1331457500346005,
+                    "total": 0.1122002499178052,
                     "count": 1,
-                    "self": 0.0007287920452654362,
+                    "self": 0.0006080828607082367,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.13241695798933506,
+                            "total": 0.11159216705709696,
                             "count": 1,
-                            "self": 0.13241695798933506
+                            "self": 0.11159216705709696
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,24 +1,24 @@
 {
     "SoccerTwos": {
-        "elo": 184.57299554666258,
+        "elo": 93.65101164083744,
         "checkpoints": [
             {
-                "steps": 178781646,
-                "file_path": "results/sept-run-01/SoccerTwos/SoccerTwos-178781646.onnx",
+                "steps": 189129132,
+                "file_path": "results/sept-run-01/SoccerTwos/SoccerTwos-189129132.onnx",
                 "reward": 0.0,
-                "creation_time": 1727130349.972419,
+                "creation_time": 1727224512.4740841,
                 "auxillary_file_paths": [
-                    "results/sept-run-01/SoccerTwos/SoccerTwos-178781646.pt"
+                    "results/sept-run-01/SoccerTwos/SoccerTwos-189129132.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 178781646,
+            "steps": 189129132,
             "file_path": "results/sept-run-01/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1727130349.972419,
+            "creation_time": 1727224512.4740841,
             "auxillary_file_paths": [
-                "results/sept-run-01/SoccerTwos/SoccerTwos-178781646.pt"
+                "results/sept-run-01/SoccerTwos/SoccerTwos-189129132.pt"
             ]
         }
     },