First Push`

README.md

@@ -0,0 +1,35 @@
+---
+library_name: ml-agents
+tags:
+- SoccerTwos
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-SoccerTwos
+---
+
+  # **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://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
+
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+  - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
+  browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
+  - A *longer tutorial* to understand how works ML-Agents:
+  https://huggingface.co/learn/deep-rl-course/unit5/introduction
+
+  ### Resume the training
+  ```bash
+  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. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
+  2. Step 1: Find your model_id: JoshCarus0/MegaMiner
+  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 sha256:408a6d35c5b64fa53c3a91e3c7e757fe87a986ede42f66887292abdf986a07c5
+size 891096

SoccerTwos/SoccerTwos-6999812.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4564b5d62bfc55a9de980fc9ba5de4426f6699b836edf226e230e44999bf96c
+size 891096

SoccerTwos/SoccerTwos-6999812.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd1b1b4c2bcebcf9ca6544019d59accdfd212d4832914bf11059816314585cef
+size 10315430

SoccerTwos/SoccerTwos-7499952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71d45ad1ee2e9f503343dc7f14a9a9297bc0930e9ebd95039b5974a3fb8f0d98
+size 891096

SoccerTwos/SoccerTwos-7499952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b77e70d901e4fba8024bdfc88f989609c3a71691199bf7339ce67b077e833d22
+size 10315430

SoccerTwos/SoccerTwos-7999930.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:580ac33de6adb303fc3ecdd7698296cca7b5dd9d0cc6701da309486917b2e586
+size 891096

SoccerTwos/SoccerTwos-7999930.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e460e2b214568199906dc65fea6cee2a50a060a7c8daf34e74881bef2c02fc44
+size 10315430

SoccerTwos/SoccerTwos-8499895.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa2aa49291cf86c20704fa57164ecb18ac602a095f9a1789730d2c3658d66700
+size 891096

SoccerTwos/SoccerTwos-8499895.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:495c08c5d0701f7f3058c16e879f4ab53b41beb4ab1567ee482da22e0ea2b0a3
+size 10315430

SoccerTwos/SoccerTwos-8534108.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:408a6d35c5b64fa53c3a91e3c7e757fe87a986ede42f66887292abdf986a07c5
+size 891096

SoccerTwos/SoccerTwos-8534108.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d0158110bab2283f924612225e7df006c213381292f130ec67c0f5c0b76e79d
+size 10315430

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4c871c009045cb9ae94eaa7aa9341a4647c231c85947116cc34e5b2c8cd95be
+size 10314310

SoccerTwos/events.out.tfevents.1699147132.DESKTOP-BDCLF9M.9240.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c64d356212e41404b80a9f000234242e7968e27db456ed2aba98777f0e05ffe
+size 8551359

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 5000, "buffer_size": 50000, "learning_rate": 0.001, "beta": 0.005, "epsilon": 0.25, "lambd": 0.93, "num_epoch": 10, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 3, "vis_encode_type": "match3", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.98, "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": 2000000000, "time_horizon": 500, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 20000, "swap_steps": 10000, "window": 10, "play_against_latest_model_ratio": 0.55, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos/SoccerTwos/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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Match3X", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,83 @@
+default_settings: null
+behaviors:
+  SoccerTwos:
+    trainer_type: poca
+    hyperparameters:
+      batch_size: 5000
+      buffer_size: 50000
+      learning_rate: 0.001
+      beta: 0.005
+      epsilon: 0.25
+      lambd: 0.93
+      num_epoch: 10
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 500000
+    network_settings:
+      normalize: false
+      hidden_units: 256
+      num_layers: 3
+      vis_encode_type: match3
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.98
+        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: 2000000000
+    time_horizon: 500
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 50000
+      team_change: 20000
+      swap_steps: 10000
+      window: 10
+      play_against_latest_model_ratio: 0.55
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/SoccerTwos/SoccerTwos/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
+environment_parameters: null
+checkpoint_settings:
+  run_id: Match3X
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,637 @@
+Mono path[0] = 'C:/Users/JoshC/Desktop/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = 'C:/Users/JoshC/Desktop/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos/MonoBleedingEdge/etc'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path C:/Users/JoshC/Desktop/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos/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  0.070 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)
+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: 0.755000 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
+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]: 169083 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
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 369 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 67.1 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 54 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 54 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 54 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 54 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 54 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 14]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 54 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_Job.Worker 13]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 8
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 54 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 54 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 54 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 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 15
+      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 54 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 54 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 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 10]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 11]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 12]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 54 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 0.9 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 169084 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 5.0 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 169084 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.3 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 0.9 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 169083 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]: 169084 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 173.6 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 2
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.9 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 169084 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]: 169083 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
+      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 0.9 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 169084 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]: 169083 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 +1,368 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 1.285967230796814,
+            "min": 1.2675200700759888,
+            "max": 3.295814037322998,
+            "count": 853
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 25966.25,
+            "min": 22325.609375,
+            "max": 105466.03125,
+            "count": 853
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 97.84313725490196,
+            "min": 49.05940594059406,
+            "max": 925.0,
+            "count": 853
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19960.0,
+            "min": 5364.0,
+            "max": 29600.0,
+            "count": 853
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1480.4279381383674,
+            "min": 1196.131789494324,
+            "max": 1522.0611629451164,
+            "count": 850
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 151003.64969011347,
+            "min": 2392.263578988648,
+            "max": 295950.4051838331,
+            "count": 850
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 8529926.0,
+            "min": 9816.0,
+            "max": 8529926.0,
+            "count": 853
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 8529926.0,
+            "min": 9816.0,
+            "max": 8529926.0,
+            "count": 853
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": 0.020283233374357224,
+            "min": -0.1126069724559784,
+            "max": 0.12560239434242249,
+            "count": 853
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": 2.0486066341400146,
+            "min": -15.31454849243164,
+            "max": 15.44909381866455,
+            "count": 853
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.01970083825290203,
+            "min": -0.11717960238456726,
+            "max": 0.12388100475072861,
+            "count": 853
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 1.9897847175598145,
+            "min": -15.936426162719727,
+            "max": 15.237363815307617,
+            "count": 853
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 853
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 853
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.055607922006361554,
+            "min": -0.5,
+            "max": 0.500690323203021,
+            "count": 853
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 5.616400122642517,
+            "min": -51.106799960136414,
+            "max": 50.08020043373108,
+            "count": 853
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.055607922006361554,
+            "min": -0.5,
+            "max": 0.500690323203021,
+            "count": 853
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 5.616400122642517,
+            "min": -51.106799960136414,
+            "max": 50.08020043373108,
+            "count": 853
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 853
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 853
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.0493208258546656,
+            "min": 0.0114828991171089,
+            "max": 0.0493208258546656,
+            "count": 170
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.0493208258546656,
+            "min": 0.0114828991171089,
+            "max": 0.0493208258546656,
+            "count": 170
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.029093711879104377,
+            "min": 0.0011735607974696905,
+            "max": 0.03776841139420867,
+            "count": 170
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.029093711879104377,
+            "min": 0.0011735607974696905,
+            "max": 0.03776841139420867,
+            "count": 170
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.031326058581471444,
+            "min": 0.0011769584967987613,
+            "max": 0.04217576038092375,
+            "count": 170
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.031326058581471444,
+            "min": 0.0011769584967987613,
+            "max": 0.04217576038092375,
+            "count": 170
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0009957384654261535,
+            "min": 0.0009957384654261535,
+            "max": 0.0009999748010025198,
+            "count": 170
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0009957384654261535,
+            "min": 0.0009957384654261535,
+            "max": 0.0009999748010025198,
+            "count": 170
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.2493607697499999,
+            "min": 0.2493607697499999,
+            "max": 0.2499962201499999,
+            "count": 170
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.2493607697499999,
+            "min": 0.2493607697499999,
+            "max": 0.2499962201499999,
+            "count": 170
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.004978734940349999,
+            "min": 0.004978734940349999,
+            "max": 0.00499987425699,
+            "count": 170
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.004978734940349999,
+            "min": 0.004978734940349999,
+            "max": 0.00499987425699,
+            "count": 170
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1699147128",
+        "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\\JoshC\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos/SoccerTwos.exe --run-id=Match3X --no-graphics",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.1.0+cu118",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1699162773"
+    },
+    "total": 15644.935624699996,
+    "count": 1,
+    "self": 4.19003050000174,
+    "children": {
+        "run_training.setup": {
+            "total": 0.14043479999236297,
+            "count": 1,
+            "self": 0.14043479999236297
+        },
+        "TrainerController.start_learning": {
+            "total": 15640.605159400002,
+            "count": 1,
+            "self": 8.876793300325517,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 8.399447100047837,
+                    "count": 423,
+                    "self": 8.399447100047837
+                },
+                "TrainerController.advance": {
+                    "total": 15623.215789099617,
+                    "count": 605029,
+                    "self": 9.197971106797922,
+                    "children": {
+                        "env_step": {
+                            "total": 8817.819561292636,
+                            "count": 605029,
+                            "self": 4854.33211369683,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 3957.8022943981923,
+                                    "count": 605029,
+                                    "self": 63.435529397349455,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 3894.366765000843,
+                                            "count": 1127378,
+                                            "self": 3894.366765000843
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 5.685153197613545,
+                                    "count": 605028,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 15625.389314606888,
+                                            "count": 605028,
+                                            "is_parallel": true,
+                                            "self": 11742.094659000679,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.4215285999234766,
+                                                    "count": 846,
+                                                    "is_parallel": true,
+                                                    "self": 0.07961020030779764,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.34191839961567894,
+                                                            "count": 3384,
+                                                            "is_parallel": true,
+                                                            "self": 0.34191839961567894
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 3882.8731270062854,
+                                                    "count": 605028,
+                                                    "is_parallel": true,
+                                                    "self": 195.46075548956287,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 156.97058519966959,
+                                                            "count": 605028,
+                                                            "is_parallel": true,
+                                                            "self": 156.97058519966959
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 2948.478467908775,
+                                                            "count": 605028,
+                                                            "is_parallel": true,
+                                                            "self": 2948.478467908775
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 581.9633184082777,
+                                                            "count": 1210056,
+                                                            "is_parallel": true,
+                                                            "self": 112.42234582995297,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 469.5409725783247,
+                                                                    "count": 4840224,
+                                                                    "is_parallel": true,
+                                                                    "self": 469.5409725783247
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 6796.198256700183,
+                            "count": 605028,
+                            "self": 61.92319880602008,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 2843.9778707941587,
+                                    "count": 605028,
+                                    "self": 2842.233458594157,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 1.744412200001534,
+                                            "count": 17,
+                                            "self": 1.744412200001534
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 3890.2971871000045,
+                                    "count": 170,
+                                    "self": 2448.599131897863,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 1441.6980552021414,
+                                            "count": 17000,
+                                            "self": 1441.6980552021414
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 7.00005330145359e-07,
+                    "count": 1,
+                    "self": 7.00005330145359e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.1131292000063695,
+                    "count": 1,
+                    "self": 0.004963100014720112,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.10816609999164939,
+                            "count": 1,
+                            "self": 0.10816609999164939
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 6999812,
+                "file_path": "results\\Match3X\\SoccerTwos\\SoccerTwos-6999812.onnx",
+                "reward": 0.0,
+                "creation_time": 1699160188.0734613,
+                "auxillary_file_paths": [
+                    "results\\Match3X\\SoccerTwos\\SoccerTwos-6999812.pt"
+                ]
+            },
+            {
+                "steps": 7499952,
+                "file_path": "results\\Match3X\\SoccerTwos\\SoccerTwos-7499952.onnx",
+                "reward": 0.0,
+                "creation_time": 1699161021.0527692,
+                "auxillary_file_paths": [
+                    "results\\Match3X\\SoccerTwos\\SoccerTwos-7499952.pt"
+                ]
+            },
+            {
+                "steps": 7999930,
+                "file_path": "results\\Match3X\\SoccerTwos\\SoccerTwos-7999930.onnx",
+                "reward": 0.0,
+                "creation_time": 1699161842.2774432,
+                "auxillary_file_paths": [
+                    "results\\Match3X\\SoccerTwos\\SoccerTwos-7999930.pt"
+                ]
+            },
+            {
+                "steps": 8499895,
+                "file_path": "results\\Match3X\\SoccerTwos\\SoccerTwos-8499895.onnx",
+                "reward": 0.0,
+                "creation_time": 1699162652.546614,
+                "auxillary_file_paths": [
+                    "results\\Match3X\\SoccerTwos\\SoccerTwos-8499895.pt"
+                ]
+            },
+            {
+                "steps": 8534108,
+                "file_path": "results\\Match3X\\SoccerTwos\\SoccerTwos-8534108.onnx",
+                "reward": 0.0,
+                "creation_time": 1699162769.409339,
+                "auxillary_file_paths": [
+                    "results\\Match3X\\SoccerTwos\\SoccerTwos-8534108.pt"
+                ]
+            }
+        ],
+        "elo": 1480.4279381383672,
+        "final_checkpoint": {
+            "steps": 8534108,
+            "file_path": "results\\Match3X\\SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1699162769.409339,
+            "auxillary_file_paths": [
+                "results\\Match3X\\SoccerTwos\\SoccerTwos-8534108.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.1.0+cu118"
+    }
+}