normalized and lower learning rate

README.md

@@ -0,0 +1,31 @@
+
+---
+      tags:
+      - unity-ml-agents
+      - ml-agents
+      - deep-reinforcement-learning
+      - reinforcement-learning
+      - ML-Agents-SoccerTwos
+      library_name: ml-agents
+---
+    
+  # **poca** Agent playing **SoccerTwos**
+  This is a trained model of a **poca** agent playing **SoccerTwos** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
+  
+  ## Usage (with ML-Agents)
+  The Documentation: https://github.com/huggingface/ml-agents#get-started
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+
+
+  ### Resume the training
+  ```
+  mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
+  ```
+  ### Watch your Agent play
+  You can watch your agent **playing directly in your browser:**.
+  
+  1. Go to https://huggingface.co/spaces/unity/ML-Agents-SoccerTwos
+  2. Step 1: Write your model_id: CoreyMorris/poca-SoccerTwos-be-the-goldfish
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

SoccerTwos.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37bb02b9fca5c6dcf8a9c6c9eddb27affcaffb78ed52796661a1b2b04d5f54c4
+size 1768041

SoccerTwos/SoccerTwos-19499964.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c18b6a759f5db56b375e54d1111b8a1d6a84041846a02f131a134c3c8017fdb1
+size 1768041

SoccerTwos/SoccerTwos-19499964.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63761e825882ae269749b188d5ac682cc780f5d1d8d2582eb73061a00c21b2e1
+size 28434289

SoccerTwos/SoccerTwos-19999902.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78bbd29552c701d484a13f99979018203fc27c161f00d0f8c06a954b7dfa9d96
+size 1768041

SoccerTwos/SoccerTwos-19999902.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0de3694bb30736dcb7cbd85638ac6056992a4d50cdc988203c561b68616736a6
+size 28434289

SoccerTwos/SoccerTwos-20499952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce5a155b215bd32ea05f9092e3ef35f6d63df8fea7ea8035182b4d25d0325ca1
+size 1768041

SoccerTwos/SoccerTwos-20499952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fcfcef99fbec6a25ae01f7f26ae97b2acd60ed8b82574a2661df481ff03f82a
+size 28434289

SoccerTwos/SoccerTwos-20999814.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bec2f676bebfd0e242aedf5e93e442997212824e741e3c2162300382944e6e35
+size 1768041

SoccerTwos/SoccerTwos-20999814.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bab8a77c69a50124f32503ae0d9e3ca1d2459ebebbf6c5eee124c30f2bed741
+size 28434289

SoccerTwos/SoccerTwos-21058676.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37bb02b9fca5c6dcf8a9c6c9eddb27affcaffb78ed52796661a1b2b04d5f54c4
+size 1768041

SoccerTwos/SoccerTwos-21058676.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38c96508c041f787685e472d3b729e3cc4c210460cc7342d92f975f49d08f278
+size 28434289

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38c96508c041f787685e472d3b729e3cc4c210460cc7342d92f975f49d08f278
+size 28434289

SoccerTwos/events.out.tfevents.1675748306.corey-ubuntu.161450.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ae56ac6ac034c35790f1d67810ccbf6f8447cf05870e845108c023d11a0049a
+size 21606364

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.00025, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 2, "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": 30000000, "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", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20.0, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos-normalized-lower-LR", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,82 @@
+default_settings: null
+behaviors:
+  SoccerTwos:
+    trainer_type: poca
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.00025
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: constant
+      beta_schedule: constant
+      epsilon_schedule: constant
+    checkpoint_interval: 500000
+    network_settings:
+      normalize: true
+      hidden_units: 512
+      num_layers: 2
+      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: 30000000
+    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
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20.0
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+environment_parameters: null
+checkpoint_settings:
+  run_id: SoccerTwos-normalized-lower-LR
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: true
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,498 @@
+Mono path[0] = '/home/corey/reinforcement-learning/hf-rl/ml-agents/training-envs-executables/SoccerTwos_Data/Managed'
+Mono config path = '/home/corey/reinforcement-learning/hf-rl/ml-agents/training-envs-executables/SoccerTwos_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /home/corey/reinforcement-learning/hf-rl/ml-agents/training-envs-executables/SoccerTwos_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.074 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)
+WARNING: Shader Unsupported: 'Standard (Specular setup)' - 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?
+ERROR: Shader Standard (Specular setup) shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard (Specular setup)' - 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?
+WARNING: Shader Unsupported: 'Autodesk Interactive' - 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?
+ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - 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?
+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?
+ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+UnloadTime: 1.100053 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+requesting resize 84 x 84
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+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 6 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]: 396778 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 300.0 KB
+      Peak Allocated Bytes 249.6 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 0.7 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 6
+      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 11
+      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_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_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 3
+    [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]: 396779 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]: 396779 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.4 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]: 396778 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]: 396779 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]: 396779 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]: 396778 frames, [4.0 MB-8.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 2
+      Peak Allocated memory 4.5 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]: 396779 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]: 396778 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

@@ -0,0 +1,424 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 1.4202992916107178,
+            "min": 1.3715102672576904,
+            "max": 3.2957284450531006,
+            "count": 2105
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 29814.923828125,
+            "min": 25090.8828125,
+            "max": 119525.6875,
+            "count": 2105
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 67.84931506849315,
+            "min": 43.18421052631579,
+            "max": 957.1666666666666,
+            "count": 2105
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19812.0,
+            "min": 15964.0,
+            "max": 24232.0,
+            "count": 2105
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1590.0963432620047,
+            "min": 1197.2260432559879,
+            "max": 1625.9444415632584,
+            "count": 2105
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 232154.06611625268,
+            "min": 2401.895577702849,
+            "max": 332658.4941263424,
+            "count": 2105
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 21049980.0,
+            "min": 9136.0,
+            "max": 21049980.0,
+            "count": 2105
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 21049980.0,
+            "min": 9136.0,
+            "max": 21049980.0,
+            "count": 2105
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.026059603318572044,
+            "min": -0.13055191934108734,
+            "max": 0.2189466953277588,
+            "count": 2105
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -3.804702043533325,
+            "min": -22.34832763671875,
+            "max": 26.492549896240234,
+            "count": 2105
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.028714856132864952,
+            "min": -0.13465484976768494,
+            "max": 0.21691039204597473,
+            "count": 2105
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -4.192368984222412,
+            "min": -21.958189010620117,
+            "max": 26.246156692504883,
+            "count": 2105
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 2105
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 2105
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.030763013313894402,
+            "min": -0.7211555555048916,
+            "max": 0.4062677668638466,
+            "count": 2105
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -4.491399943828583,
+            "min": -65.21519994735718,
+            "max": 53.16879951953888,
+            "count": 2105
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.030763013313894402,
+            "min": -0.7211555555048916,
+            "max": 0.4062677668638466,
+            "count": 2105
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -4.491399943828583,
+            "min": -65.21519994735718,
+            "max": 53.16879951953888,
+            "count": 2105
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 2105
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 2105
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.01916274221633406,
+            "min": 0.011980528947121153,
+            "max": 0.02607447102976342,
+            "count": 1020
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.01916274221633406,
+            "min": 0.011980528947121153,
+            "max": 0.02607447102976342,
+            "count": 1020
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.09843031913042069,
+            "min": 0.003205703478306532,
+            "max": 0.11418496891856193,
+            "count": 1020
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.09843031913042069,
+            "min": 0.003205703478306532,
+            "max": 0.11418496891856193,
+            "count": 1020
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.10010224978129069,
+            "min": 0.0033252638997510074,
+            "max": 0.11699406206607818,
+            "count": 1020
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.10010224978129069,
+            "min": 0.0033252638997510074,
+            "max": 0.11699406206607818,
+            "count": 1020
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.00025000000000000006,
+            "min": 0.00025,
+            "max": 0.00025000000000000006,
+            "count": 1020
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.00025000000000000006,
+            "min": 0.00025,
+            "max": 0.00025000000000000006,
+            "count": 1020
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000004,
+            "max": 0.20000000000000007,
+            "count": 1020
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000004,
+            "max": 0.20000000000000007,
+            "count": 1020
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 1020
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 1020
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1675748305",
+        "python_version": "3.9.16 (main, Jan 11 2023, 16:05:54) \n[GCC 11.2.0]",
+        "command_line_arguments": "/home/corey/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos --run-id=SoccerTwos-normalized-lower-LR --no-graphics --force",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.11.0+cu102",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1675797054"
+    },
+    "total": 48749.00339973501,
+    "count": 1,
+    "self": 0.005703051996533759,
+    "children": {
+        "run_training.setup": {
+            "total": 0.009024478000355884,
+            "count": 1,
+            "self": 0.009024478000355884
+        },
+        "TrainerController.start_learning": {
+            "total": 48748.988672205014,
+            "count": 1,
+            "self": 34.51045566810353,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 5.3940780640841695,
+                    "count": 106,
+                    "self": 5.3940780640841695
+                },
+                "TrainerController.advance": {
+                    "total": 48708.80267958081,
+                    "count": 1445128,
+                    "self": 30.352071003595483,
+                    "children": {
+                        "env_step": {
+                            "total": 38488.56022446271,
+                            "count": 1445128,
+                            "self": 32194.51703249621,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 6271.667406970824,
+                                    "count": 1445128,
+                                    "self": 166.96201653964818,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 6104.705390431176,
+                                            "count": 2645236,
+                                            "self": 6104.705390431176
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 22.37578499567462,
+                                    "count": 1445128,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 48676.307165142294,
+                                            "count": 1445128,
+                                            "is_parallel": true,
+                                            "self": 20863.467530006586,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.00482367500080727,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.0012181429920019582,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.003605532008805312,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.003605532008805312
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.03585488199314568,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0010453489958308637,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0012470990041038021,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0012470990041038021
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.030874381001922302,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.030874381001922302
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.002688052991288714,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0005022849945817143,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.002185767996707,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.002185767996707
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 27812.395905797865,
+                                                    "count": 1445127,
+                                                    "is_parallel": true,
+                                                    "self": 2127.684910404583,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 1070.544038914857,
+                                                            "count": 1445127,
+                                                            "is_parallel": true,
+                                                            "self": 1070.544038914857
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 18966.60377680925,
+                                                            "count": 1445127,
+                                                            "is_parallel": true,
+                                                            "self": 18966.60377680925
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 5647.563179669174,
+                                                            "count": 2890254,
+                                                            "is_parallel": true,
+                                                            "self": 965.1065169266076,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 4682.456662742567,
+                                                                    "count": 11561016,
+                                                                    "is_parallel": true,
+                                                                    "self": 4682.456662742567
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.4437293378432514,
+                                                    "count": 210,
+                                                    "is_parallel": true,
+                                                    "self": 0.07443814404541627,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.36929119379783515,
+                                                            "count": 840,
+                                                            "is_parallel": true,
+                                                            "self": 0.36929119379783515
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 10189.890384114507,
+                            "count": 1445128,
+                            "self": 245.19157835077203,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 3795.2772716347245,
+                                    "count": 1445128,
+                                    "self": 3784.3503536866338,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 10.926917948090704,
+                                            "count": 42,
+                                            "self": 10.926917948090704
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 6149.421534129011,
+                                    "count": 1021,
+                                    "self": 3404.863370418112,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 2744.558163710899,
+                                            "count": 30627,
+                                            "self": 2744.558163710899
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 3.716995706781745e-06,
+                    "count": 1,
+                    "self": 3.716995706781745e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.28145517501980066,
+                    "count": 1,
+                    "self": 0.0015516830317210406,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.2799034919880796,
+                            "count": 1,
+                            "self": 0.2799034919880796
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 19499964,
+                "file_path": "results/SoccerTwos-normalized-lower-LR/SoccerTwos/SoccerTwos-19499964.onnx",
+                "reward": 0.0,
+                "creation_time": 1675793436.5937061,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos-normalized-lower-LR/SoccerTwos/SoccerTwos-19499964.pt"
+                ]
+            },
+            {
+                "steps": 19999902,
+                "file_path": "results/SoccerTwos-normalized-lower-LR/SoccerTwos/SoccerTwos-19999902.onnx",
+                "reward": 0.0,
+                "creation_time": 1675794591.927003,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos-normalized-lower-LR/SoccerTwos/SoccerTwos-19999902.pt"
+                ]
+            },
+            {
+                "steps": 20499952,
+                "file_path": "results/SoccerTwos-normalized-lower-LR/SoccerTwos/SoccerTwos-20499952.onnx",
+                "reward": 0.0,
+                "creation_time": 1675795751.0682557,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos-normalized-lower-LR/SoccerTwos/SoccerTwos-20499952.pt"
+                ]
+            },
+            {
+                "steps": 20999814,
+                "file_path": "results/SoccerTwos-normalized-lower-LR/SoccerTwos/SoccerTwos-20999814.onnx",
+                "reward": 0.0,
+                "creation_time": 1675796915.7629673,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos-normalized-lower-LR/SoccerTwos/SoccerTwos-20999814.pt"
+                ]
+            },
+            {
+                "steps": 21058676,
+                "file_path": "results/SoccerTwos-normalized-lower-LR/SoccerTwos/SoccerTwos-21058676.onnx",
+                "reward": null,
+                "creation_time": 1675797054.1001306,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos-normalized-lower-LR/SoccerTwos/SoccerTwos-21058676.pt"
+                ]
+            }
+        ],
+        "elo": 1593.496482206595,
+        "final_checkpoint": {
+            "steps": 21058676,
+            "file_path": "results/SoccerTwos-normalized-lower-LR/SoccerTwos.onnx",
+            "reward": null,
+            "creation_time": 1675797054.1001306,
+            "auxillary_file_paths": [
+                "results/SoccerTwos-normalized-lower-LR/SoccerTwos/SoccerTwos-21058676.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}