First Push`

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fcada14cfe407b47020b323f2a3a26e2370cbc53dae682a23088018152a9286
+oid sha256:eef4772831c447c378724b474a92443cf54250e0551aa5e681344e0b9a1e5112
 size 2820313

SoccerTwos/SoccerTwos-34499925.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec684ef047f0211f2c229c5121c175f9df131028b6db4a936dde925ad35cb4d9
+size 2820313

SoccerTwos/SoccerTwos-34499925.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a60064224a109f33cba187aefd0079e245bfed73dca178aa363ad483ff1c7b5a
+size 34741042

SoccerTwos/SoccerTwos-34999965.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fabe1cfa9676bebc2535bf72ea533fba7e61aaf66b5448a65b2916103467049
+size 2820313

SoccerTwos/SoccerTwos-34999965.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6688dc70a26e01ffe0cf0b1469aabd060d69f3933098d171fd830c91e7fd1ca8
+size 34741042

SoccerTwos/SoccerTwos-35499943.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a9ab6c21d057fcf6c1a97c00eb5156b7add4fad4c589e028676258c61666218
+size 2820313

SoccerTwos/SoccerTwos-35499943.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec3ea026a68f8293406601e2528f313ed6f3616ff1c6c6f7f8cefef0c8e2d9bc
+size 34741042

SoccerTwos/SoccerTwos-35999947.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:415fd8a91d9bff42b577fc6946fcee8f1f85c42d1d1f5a45fedbbf2d82461350
+size 2820313

SoccerTwos/SoccerTwos-35999947.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dcadde1bf808ffec51ac18ea090bb6b1163279de58c1f0e004d0c8e0fa5b1a7
+size 34741042

SoccerTwos/SoccerTwos-36122471.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eef4772831c447c378724b474a92443cf54250e0551aa5e681344e0b9a1e5112
+size 2820313

SoccerTwos/SoccerTwos-36122471.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dad6cb5b975833346e1743ef0d59909dece0bf0c37807b6211c88862f164e066
+size 34741042

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cf474902b4856e456f06bf430a4fd858e1e42e473d5f53ebf2930df3c6d594c
+oid sha256:fc4489cf29ffb1b599687198ffcb442ff7a7d4dc5ed489d2780b89c36a1ada7b
 size 34739782

SoccerTwos/events.out.tfevents.1717346120.BlackPC.12836.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8bbf7fc3ffc237381b9d585c940c0fdafa76c6ea43b8f24b0b77e130aa9eb4c
+size 12395965

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0005, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 50000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.exe", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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": "SoccerTwos-v2", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": "cuda"}, "debug": false}
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0005, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 50000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.exe", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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": "SoccerTwos-v2", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": "cuda"}, "debug": false}

configuration.yaml

@@ -74,8 +74,8 @@ checkpoint_settings:
   run_id: SoccerTwos-v2
   initialize_from: null
   load_model: false
-  resume: false
-  force: true
+  resume: true
+  force: false
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -9,7 +9,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.063 seconds
+- Completed reload, in  9.634 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 Microsoft Media Foundation video decoding to texture disabled: graphics device is Null, only Direct3D 11 and Direct3D 12 (only on desktop) are supported for hardware-accelerated video decoding.
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -35,480 +35,15 @@ 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: 0.495800 ms
+UnloadTime: 0.625800 ms
 Registered Communicator in Agent.
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
 Setting up 8 worker threads for Enlighten.
 Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 453673 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 227225 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -521,7 +56,7 @@ Memory Statistics:
     [ALLOC_TEMP_Loading.PreloadManager]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 68.0 KB
+      Peak Allocated Bytes 67.1 KB
       Overflow Count 4
     [ALLOC_TEMP_Background Job.Worker 8]
       Initial Block Size 32.0 KB
@@ -531,7 +66,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 6]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 488 B
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Job.Worker 0]
       Initial Block Size 256.0 KB
@@ -676,7 +211,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 11]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 54 B
+      Peak Allocated Bytes 488 B
       Overflow Count 0
     [ALLOC_TEMP_Job.Worker 12]
       Initial Block Size 256.0 KB
@@ -694,22 +229,22 @@ Memory Statistics:
       Peak Allocated Bytes 54 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 3
+  Peak main deferred allocation count 6
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 453674 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 227226 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 5.0 MB
+      Peak Allocated memory 5.2 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 453674 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 227226 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.4 MB
+      Peak Allocated memory 17.3 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -738,13 +273,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 453673 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 227225 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]: 453674 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 227226 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.6 KB
@@ -756,13 +291,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 453674 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 227226 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]: 453673 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 227225 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 3.2 MB
@@ -774,13 +309,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 453674 frames
+      Peak usage frame count: [0-1.0 KB]: 227226 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]: 453673 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 227225 frames, [2.0 KB-4.0 KB]: 1 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 2.2 KB

run_logs/timers.json

@@ -2,305 +2,305 @@
     "name": "root",
     "gauges": {
         "SoccerTwos.Policy.Entropy.mean": {
-            "value": 1.6636180877685547,
-            "min": 1.594543218612671,
-            "max": 3.295814037322998,
-            "count": 2406
+            "value": 1.5932320356369019,
+            "min": 1.5016505718231201,
+            "max": 1.745996356010437,
+            "count": 1206
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 31036.458984375,
-            "min": 15368.1796875,
-            "max": 118472.203125,
-            "count": 2406
+            "value": 31048.90625,
+            "min": 25631.4140625,
+            "max": 41233.62890625,
+            "count": 1206
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 85.72413793103448,
-            "min": 43.93636363636364,
-            "max": 999.0,
-            "count": 2406
+            "value": 71.3768115942029,
+            "min": 45.28440366972477,
+            "max": 119.14285714285714,
+            "count": 1206
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19888.0,
-            "min": 11108.0,
-            "max": 29216.0,
-            "count": 2406
+            "value": 19700.0,
+            "min": 13156.0,
+            "max": 22016.0,
+            "count": 1206
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1565.2804519784434,
-            "min": 1197.1631316239868,
-            "max": 1642.0178183662626,
-            "count": 2399
+            "value": 1529.4984329634783,
+            "min": 1477.5859388363544,
+            "max": 1612.6695298792558,
+            "count": 1206
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 181572.53242949944,
-            "min": 2396.073972986234,
-            "max": 343095.51331827336,
-            "count": 2399
+            "value": 211070.78374896,
+            "min": 128689.4620998312,
+            "max": 329568.675261479,
+            "count": 1206
         },
         "SoccerTwos.Step.mean": {
-            "value": 24059970.0,
-            "min": 9624.0,
-            "max": 24059970.0,
-            "count": 2406
+            "value": 36119914.0,
+            "min": 24069963.0,
+            "max": 36119914.0,
+            "count": 1206
         },
         "SoccerTwos.Step.sum": {
-            "value": 24059970.0,
-            "min": 9624.0,
-            "max": 24059970.0,
-            "count": 2406
+            "value": 36119914.0,
+            "min": 24069963.0,
+            "max": 36119914.0,
+            "count": 1206
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": -0.041980259120464325,
-            "min": -0.14346793293952942,
-            "max": 0.15887333452701569,
-            "count": 2406
+            "value": -0.028788791969418526,
+            "min": -0.14242351055145264,
+            "max": 0.08708593994379044,
+            "count": 1206
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": -4.9116902351379395,
-            "min": -24.939861297607422,
-            "max": 24.154552459716797,
-            "count": 2406
+            "value": -3.972853183746338,
+            "min": -20.651409149169922,
+            "max": 10.431331634521484,
+            "count": 1206
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.043714605271816254,
-            "min": -0.14875417947769165,
-            "max": 0.15854130685329437,
-            "count": 2406
+            "value": -0.03223952651023865,
+            "min": -0.14488904178142548,
+            "max": 0.08526767045259476,
+            "count": 1206
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -5.1146087646484375,
-            "min": -25.734474182128906,
-            "max": 23.633056640625,
-            "count": 2406
+            "value": -4.449054718017578,
+            "min": -21.0089111328125,
+            "max": 11.612297058105469,
+            "count": 1206
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 2406
+            "count": 1206
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 2406
+            "count": 1206
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.16922735098080757,
-            "min": -0.6012000026447433,
-            "max": 0.4812399983406067,
-            "count": 2406
+            "value": -0.18953768109929733,
+            "min": -0.45386880111694333,
+            "max": 0.33275094234718466,
+            "count": 1206
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -19.799600064754486,
-            "min": -82.87199997901917,
-            "max": 58.285200238227844,
-            "count": 2406
+            "value": -26.156199991703033,
+            "min": -57.70319998264313,
+            "max": 43.89559996128082,
+            "count": 1206
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.16922735098080757,
-            "min": -0.6012000026447433,
-            "max": 0.4812399983406067,
-            "count": 2406
+            "value": -0.18953768109929733,
+            "min": -0.45386880111694333,
+            "max": 0.33275094234718466,
+            "count": 1206
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -19.799600064754486,
-            "min": -82.87199997901917,
-            "max": 58.285200238227844,
-            "count": 2406
+            "value": -26.156199991703033,
+            "min": -57.70319998264313,
+            "max": 43.89559996128082,
+            "count": 1206
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 2406
+            "count": 1206
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 2406
+            "count": 1206
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.026724799117073417,
-            "min": 0.011645330385848258,
-            "max": 0.030771676887525246,
-            "count": 1165
+            "value": 0.02783555166485409,
+            "min": 0.022215450095245615,
+            "max": 0.03516377701113622,
+            "count": 584
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.026724799117073417,
-            "min": 0.011645330385848258,
-            "max": 0.030771676887525246,
-            "count": 1165
+            "value": 0.02783555166485409,
+            "min": 0.022215450095245615,
+            "max": 0.03516377701113622,
+            "count": 584
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.07742057542006174,
-            "min": 9.073131647407233e-05,
-            "max": 0.10896282270550728,
-            "count": 1165
+            "value": 0.08402746667464574,
+            "min": 0.05958654967447122,
+            "max": 0.10001727566123009,
+            "count": 584
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.07742057542006174,
-            "min": 9.073131647407233e-05,
-            "max": 0.10896282270550728,
-            "count": 1165
+            "value": 0.08402746667464574,
+            "min": 0.05958654967447122,
+            "max": 0.10001727566123009,
+            "count": 584
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.078636467953523,
-            "min": 9.011629032708394e-05,
-            "max": 0.11352330520749092,
-            "count": 1165
+            "value": 0.08519837260246277,
+            "min": 0.06038877206544081,
+            "max": 0.10178241382042567,
+            "count": 584
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.078636467953523,
-            "min": 9.011629032708394e-05,
-            "max": 0.11352330520749092,
-            "count": 1165
+            "value": 0.08519837260246277,
+            "min": 0.06038877206544081,
+            "max": 0.10178241382042567,
+            "count": 584
         },
         "SoccerTwos.Policy.LearningRate.mean": {
             "value": 0.0005000000000000001,
             "min": 0.0005000000000000001,
             "max": 0.0005000000000000001,
-            "count": 1165
+            "count": 584
         },
         "SoccerTwos.Policy.LearningRate.sum": {
             "value": 0.0005000000000000001,
             "min": 0.0005000000000000001,
             "max": 0.0005000000000000001,
-            "count": 1165
+            "count": 584
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.20000000000000007,
             "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 1165
+            "count": 584
         },
         "SoccerTwos.Policy.Epsilon.sum": {
             "value": 0.20000000000000007,
             "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 1165
+            "count": 584
         },
         "SoccerTwos.Policy.Beta.mean": {
             "value": 0.005000000000000001,
             "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 1165
+            "count": 584
         },
         "SoccerTwos.Policy.Beta.sum": {
             "value": 0.005000000000000001,
             "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 1165
+            "count": 584
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1717312503",
+        "start_time_seconds": "1717346107",
         "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul  5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]",
-        "command_line_arguments": "\\\\?\\C:\\Users\\Jeste\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos-v2 --no-graphics --torch-device cuda --force",
+        "command_line_arguments": "\\\\?\\C:\\Users\\Jeste\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos-v2 --no-graphics --torch-device cuda --resume",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.3.0",
         "numpy_version": "1.24.3",
-        "end_time_seconds": "1717345770"
+        "end_time_seconds": "1717363014"
     },
-    "total": 33266.6872347,
+    "total": 16907.010431599992,
     "count": 1,
-    "self": 0.8471069999941392,
+    "self": 0.0491213999921456,
     "children": {
         "run_training.setup": {
-            "total": 0.06998500000918284,
+            "total": 0.08449160000600386,
             "count": 1,
-            "self": 0.06998500000918284
+            "self": 0.08449160000600386
         },
         "TrainerController.start_learning": {
-            "total": 33265.7701427,
+            "total": 16906.876818599994,
             "count": 1,
-            "self": 20.592532311420655,
+            "self": 10.754153696529102,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 5.9628254999552155,
-                    "count": 121,
-                    "self": 5.9628254999552155
+                    "total": 15.293022299854783,
+                    "count": 62,
+                    "self": 15.293022299854783
                 },
                 "TrainerController.advance": {
-                    "total": 33239.04071348862,
-                    "count": 1645709,
-                    "self": 19.696258394484175,
+                    "total": 16880.695971903595,
+                    "count": 819248,
+                    "self": 10.736753806617344,
                     "children": {
                         "env_step": {
-                            "total": 24023.407298192906,
-                            "count": 1645709,
-                            "self": 12820.14125148987,
+                            "total": 12331.277499803007,
+                            "count": 819248,
+                            "self": 6652.798938405846,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 11190.55515350915,
-                                    "count": 1645709,
-                                    "self": 143.87588241879712,
+                                    "total": 5671.828558090914,
+                                    "count": 819248,
+                                    "self": 76.0575644809287,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 11046.679271090354,
-                                            "count": 3024540,
-                                            "self": 11046.679271090354
+                                            "total": 5595.770993609985,
+                                            "count": 1514862,
+                                            "self": 5595.770993609985
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 12.710893193885568,
-                                    "count": 1645709,
+                                    "total": 6.650003306247527,
+                                    "count": 819247,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 33234.65843979569,
-                                            "count": 1645709,
+                                            "total": 16879.08530110467,
+                                            "count": 819247,
                                             "is_parallel": true,
-                                            "self": 23052.050574604684,
+                                            "self": 11573.817548899926,
                                             "children": {
                                                 "steps_from_proto": {
-                                                    "total": 0.1480563999793958,
-                                                    "count": 242,
+                                                    "total": 0.08027969991962891,
+                                                    "count": 124,
                                                     "is_parallel": true,
-                                                    "self": 0.029115000157617033,
+                                                    "self": 0.014920400179107673,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.11894139982177876,
-                                                            "count": 968,
+                                                            "total": 0.06535929974052124,
+                                                            "count": 496,
                                                             "is_parallel": true,
-                                                            "self": 0.11894139982177876
+                                                            "self": 0.06535929974052124
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 10182.459808791027,
-                                                    "count": 1645709,
+                                                    "total": 5305.187472504826,
+                                                    "count": 819247,
                                                     "is_parallel": true,
-                                                    "self": 602.4294308170938,
+                                                    "self": 301.55195310743875,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 495.47019439502037,
-                                                            "count": 1645709,
+                                                            "total": 253.8752837996144,
+                                                            "count": 819247,
                                                             "is_parallel": true,
-                                                            "self": 495.47019439502037
+                                                            "self": 253.8752837996144
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 7141.594114890424,
-                                                            "count": 1645709,
+                                                            "total": 3780.561313590748,
+                                                            "count": 819247,
                                                             "is_parallel": true,
-                                                            "self": 7141.594114890424
+                                                            "self": 3780.561313590748
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 1942.966068688489,
-                                                            "count": 3291418,
+                                                            "total": 969.1989220070245,
+                                                            "count": 1638494,
                                                             "is_parallel": true,
-                                                            "self": 368.45853984532005,
+                                                            "self": 185.13892348716035,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 1574.507528843169,
-                                                                    "count": 13165672,
+                                                                    "total": 784.0599985198642,
+                                                                    "count": 6553976,
                                                                     "is_parallel": true,
-                                                                    "self": 1574.507528843169
+                                                                    "self": 784.0599985198642
                                                                 }
                                                             }
                                                         }
@@ -313,31 +313,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 9195.93715690123,
-                            "count": 1645709,
-                            "self": 197.81395890460408,
+                            "total": 4538.68171829397,
+                            "count": 819247,
+                            "self": 105.74872958290507,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 4771.658420996857,
-                                    "count": 1645709,
-                                    "self": 4763.868793196802,
+                                    "total": 2295.629787311045,
+                                    "count": 819247,
+                                    "self": 2291.5712614110817,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 7.789627800055314,
-                                            "count": 48,
-                                            "self": 7.789627800055314
+                                            "total": 4.05852589996357,
+                                            "count": 24,
+                                            "self": 4.05852589996357
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 4226.464776999768,
-                                    "count": 1165,
-                                    "self": 2660.2023248016776,
+                                    "total": 2137.30320140002,
+                                    "count": 585,
+                                    "self": 1320.8601817983872,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 1566.2624521980906,
-                                            "count": 34950,
-                                            "self": 1566.2624521980906
+                                            "total": 816.4430196016328,
+                                            "count": 17550,
+                                            "self": 816.4430196016328
                                         }
                                     }
                                 }
@@ -351,14 +351,14 @@
                     "self": 9.00006853044033e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.1740704999974696,
+                    "total": 0.13366980000864714,
                     "count": 1,
-                    "self": 0.006139899996924214,
+                    "self": 0.006770200008759275,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.16793060000054538,
+                            "total": 0.12689959999988787,
                             "count": 1,
-                            "self": 0.16793060000054538
+                            "self": 0.12689959999988787
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,59 +2,59 @@
     "SoccerTwos": {
         "checkpoints": [
             {
-                "steps": 22499982,
-                "file_path": "results\\SoccerTwos-v2\\SoccerTwos\\SoccerTwos-22499982.onnx",
+                "steps": 34499925,
+                "file_path": "results\\SoccerTwos-v2\\SoccerTwos\\SoccerTwos-34499925.onnx",
                 "reward": 0.0,
-                "creation_time": 1717343633.8852472,
+                "creation_time": 1717360772.3268785,
                 "auxillary_file_paths": [
-                    "results\\SoccerTwos-v2\\SoccerTwos\\SoccerTwos-22499982.pt"
+                    "results\\SoccerTwos-v2\\SoccerTwos\\SoccerTwos-34499925.pt"
                 ]
             },
             {
-                "steps": 22999818,
-                "file_path": "results\\SoccerTwos-v2\\SoccerTwos\\SoccerTwos-22999818.onnx",
+                "steps": 34999965,
+                "file_path": "results\\SoccerTwos-v2\\SoccerTwos\\SoccerTwos-34999965.onnx",
                 "reward": 0.0,
-                "creation_time": 1717344319.1450598,
+                "creation_time": 1717361456.9370532,
                 "auxillary_file_paths": [
-                    "results\\SoccerTwos-v2\\SoccerTwos\\SoccerTwos-22999818.pt"
+                    "results\\SoccerTwos-v2\\SoccerTwos\\SoccerTwos-34999965.pt"
                 ]
             },
             {
-                "steps": 23499734,
-                "file_path": "results\\SoccerTwos-v2\\SoccerTwos\\SoccerTwos-23499734.onnx",
+                "steps": 35499943,
+                "file_path": "results\\SoccerTwos-v2\\SoccerTwos\\SoccerTwos-35499943.onnx",
                 "reward": 0.0,
-                "creation_time": 1717344995.8559241,
+                "creation_time": 1717362146.0519485,
                 "auxillary_file_paths": [
-                    "results\\SoccerTwos-v2\\SoccerTwos\\SoccerTwos-23499734.pt"
+                    "results\\SoccerTwos-v2\\SoccerTwos\\SoccerTwos-35499943.pt"
                 ]
             },
             {
-                "steps": 23999860,
-                "file_path": "results\\SoccerTwos-v2\\SoccerTwos\\SoccerTwos-23999860.onnx",
+                "steps": 35999947,
+                "file_path": "results\\SoccerTwos-v2\\SoccerTwos\\SoccerTwos-35999947.onnx",
                 "reward": 0.0,
-                "creation_time": 1717345681.0811205,
+                "creation_time": 1717362840.0971513,
                 "auxillary_file_paths": [
-                    "results\\SoccerTwos-v2\\SoccerTwos\\SoccerTwos-23999860.pt"
+                    "results\\SoccerTwos-v2\\SoccerTwos\\SoccerTwos-35999947.pt"
                 ]
             },
             {
-                "steps": 24063501,
-                "file_path": "results\\SoccerTwos-v2\\SoccerTwos\\SoccerTwos-24063501.onnx",
+                "steps": 36122471,
+                "file_path": "results\\SoccerTwos-v2\\SoccerTwos\\SoccerTwos-36122471.onnx",
                 "reward": 0.0,
-                "creation_time": 1717345769.768377,
+                "creation_time": 1717363014.07278,
                 "auxillary_file_paths": [
-                    "results\\SoccerTwos-v2\\SoccerTwos\\SoccerTwos-24063501.pt"
+                    "results\\SoccerTwos-v2\\SoccerTwos\\SoccerTwos-36122471.pt"
                 ]
             }
         ],
-        "elo": 1568.4167220156785,
+        "elo": 1524.8185739091505,
         "final_checkpoint": {
-            "steps": 24063501,
+            "steps": 36122471,
             "file_path": "results\\SoccerTwos-v2\\SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1717345769.768377,
+            "creation_time": 1717363014.07278,
             "auxillary_file_paths": [
-                "results\\SoccerTwos-v2\\SoccerTwos\\SoccerTwos-24063501.pt"
+                "results\\SoccerTwos-v2\\SoccerTwos\\SoccerTwos-36122471.pt"
             ]
         }
     },