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: Lethargus/poca-SoccerTwos
+  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 sha256:83d11dcb3f7356698527d3c137a82255324d892850ce86a908c89587e631ea9f
+size 9824476

SoccerTwos/SoccerTwos-17999734.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a682093c1ce0688706a89f240bfcaa877014f239e5bf002e730ae3ebc097066e
+size 9824476

SoccerTwos/SoccerTwos-17999734.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9385180d176f903680440db2c03602b49b84d7b744950a9a21f25628911e5b9
+size 126058857

SoccerTwos/SoccerTwos-18499770.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02ce510ba6f6856d9decb18482d6396df1777ca0d49afd70fbc3173c0665a3b2
+size 9824476

SoccerTwos/SoccerTwos-18499770.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0928ce782082d8d013e7f1d8462b33e94a791e68fa49468df29604ef4528e9f4
+size 126058857

SoccerTwos/SoccerTwos-18999904.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d843809a8d3071d21ed63a64ed68f3b80c750e61fd89454ab2beef7388f38036
+size 9824476

SoccerTwos/SoccerTwos-18999904.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ef960280418a8ae40b5e407c76e1524ebe85afd009132840e249522118a8802
+size 126058857

SoccerTwos/SoccerTwos-19499952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a200afc1df7adef1a15227e09d73cd1885dcef2319d4b870aad1a9bbf2faa5b0
+size 9824476

SoccerTwos/SoccerTwos-19499952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:010f5396dc29adb324f2d663a4bf9ec68fb9a5ea8c888cc7b4b518b4cf2d4a5c
+size 126058857

SoccerTwos/SoccerTwos-19769974.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83d11dcb3f7356698527d3c137a82255324d892850ce86a908c89587e631ea9f
+size 9824476

SoccerTwos/SoccerTwos-19769974.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cb46a176cea400e9cfa9a65fcd87fbf3fa8c0edd40674f9e55d4974cb1d24fa
+size 126058857

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5342803d2879f97906b6b4e6b3aa72d4f4aef82319560783164c4658d0ccd01d
+size 126057615

SoccerTwos/events.out.tfevents.1694566782.vmgaming.1084.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2341a3530c33dee2d0309a013e10c5498a743dc8e56ecd827c5921d63d8358f6
+size 13743678

SoccerTwos/events.out.tfevents.1694602563.vmgaming.7688.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ccf4e89ecb2fa31a9ac360b5893e58d4def21adb6ea26dcfd40bc15a9c53a7a
+size 5170256

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0006, "beta": 0.01, "epsilon": 0.25, "lambd": 0.95, "num_epoch": 4, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 1024, "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": 70000000, "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": "../Soccer/Soccer.exe", "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, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTeamBest", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,82 @@
+default_settings: null
+behaviors:
+  SoccerTwos:
+    trainer_type: poca
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0006
+      beta: 0.01
+      epsilon: 0.25
+      lambd: 0.95
+      num_epoch: 4
+      learning_rate_schedule: constant
+      beta_schedule: constant
+      epsilon_schedule: constant
+    checkpoint_interval: 500000
+    network_settings:
+      normalize: false
+      hidden_units: 1024
+      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: 70000000
+    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: ../Soccer/Soccer.exe
+  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
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+environment_parameters: null
+checkpoint_settings:
+  run_id: SoccerTeamBest
+  initialize_from: null
+  load_model: false
+  resume: true
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,311 @@
+Mono path[0] = 'C:/Users/bdonn/Documents/DRL-Explore/Soccer/Soccer_Data/Managed'
+Mono config path = 'C:/Users/bdonn/Documents/DRL-Explore/Soccer/MonoBleedingEdge/etc'
+[Physics::Module] Initialized MultithreadedJobDispatcher with 3 workers.
+Initialize engine version: 2023.1.12f1 (38370f5b2257)
+[Subsystems] Discovering subsystems at path C:/Users/bdonn/Documents/DRL-Explore/Soccer/Soccer_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
+C:\build\output\Unity-Technologies\mono\mono\metadata\icall.c:1842:
+C:\build\output\Unity-Technologies\mono\mono\metadata\icall.c:1842:
+C:\build\output\Unity-Technologies\mono\mono\metadata\icall.c:1842:
+C:\build\output\Unity-Technologies\mono\mono\metadata\icall.c:1842:
+C:\build\output\Unity-Technologies\mono\mono\metadata\icall.c:1842:
+C:\build\output\Unity-Technologies\mono\mono\metadata\icall.c:1842:
+C:\build\output\Unity-Technologies\mono\mono\metadata\icall.c:1842:
+C:\build\output\Unity-Technologies\mono\mono\metadata\icall.c:1842:
+C:\build\output\Unity-Technologies\mono\mono\metadata\icall.c:1842:
+- Loaded All Assemblies, in  1.985 seconds
+C:\build\output\Unity-Technologies\mono\mono\metadata\icall.c:1842:
+C:\build\output\Unity-Technologies\mono\mono\metadata\icall.c:1842:
+- Finished resetting the current domain, in  0.001 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: '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?
+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?
+UnloadTime: 0.613000 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Setting up 2 worker threads for Enlighten.
+Memory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 95376 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_Background Job.worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 66 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 70.0 KB
+      Overflow Count 5
+    [ALLOC_TEMP_Background Job.worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 66 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 66 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 66 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 66 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 66 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 66 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 66 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 64 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 66 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 66 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 66 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 66 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 2
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 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 0.8 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 66 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 66 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 3
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 66 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 64 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 66 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 66 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 261 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 66 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 19
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.1 MB
+      Failed Allocations. Bucket layout:
+        16B: 2 Subsections = 2048 buckets. Failed count: 0
+        32B: 7 Subsections = 3584 buckets. Failed count: 0
+        48B: 194 Subsections = 66218 buckets. Failed count: 2144
+        64B: 25 Subsections = 6400 buckets. Failed count: 0
+        80B: 16 Subsections = 3276 buckets. Failed count: 0
+        96B: 3 Subsections = 512 buckets. Failed count: 0
+        112B: 2 Subsections = 292 buckets. Failed count: 0
+        128B: 7 Subsections = 896 buckets. Failed count: 0
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 95377 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 30.2 MB
+      Peak Large allocation bytes 16.0 MB
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 95377 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 5.5 MB
+      Peak Large allocation bytes 0 B
+[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 0
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 1
+  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 1.1 MB
+      Failed Allocations. Bucket layout:
+        16B: 2 Subsections = 2048 buckets. Failed count: 0
+        32B: 7 Subsections = 3584 buckets. Failed count: 0
+        48B: 194 Subsections = 66218 buckets. Failed count: 2144
+        64B: 25 Subsections = 6400 buckets. Failed count: 0
+        80B: 16 Subsections = 3276 buckets. Failed count: 0
+        96B: 3 Subsections = 512 buckets. Failed count: 0
+        112B: 2 Subsections = 292 buckets. Failed count: 0
+        128B: 7 Subsections = 896 buckets. Failed count: 0
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 95376 frames, [64.0 KB-128.0 KB]: 1 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 66.3 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [128.0 KB-256.0 KB]: 95377 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 175.7 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 1.1 MB
+      Failed Allocations. Bucket layout:
+        16B: 2 Subsections = 2048 buckets. Failed count: 0
+        32B: 7 Subsections = 3584 buckets. Failed count: 0
+        48B: 194 Subsections = 66218 buckets. Failed count: 2144
+        64B: 25 Subsections = 6400 buckets. Failed count: 0
+        80B: 16 Subsections = 3276 buckets. Failed count: 0
+        96B: 3 Subsections = 512 buckets. Failed count: 0
+        112B: 2 Subsections = 292 buckets. Failed count: 0
+        128B: 7 Subsections = 896 buckets. Failed count: 0
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 95377 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 0.7 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_CACHEOBJECTS_THREAD]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 95376 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 3.3 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 1.1 MB
+      Failed Allocations. Bucket layout:
+        16B: 2 Subsections = 2048 buckets. Failed count: 0
+        32B: 7 Subsections = 3584 buckets. Failed count: 0
+        48B: 194 Subsections = 66218 buckets. Failed count: 2144
+        64B: 25 Subsections = 6400 buckets. Failed count: 0
+        80B: 16 Subsections = 3276 buckets. Failed count: 0
+        96B: 3 Subsections = 512 buckets. Failed count: 0
+        112B: 2 Subsections = 292 buckets. Failed count: 0
+        128B: 7 Subsections = 896 buckets. Failed count: 0
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [4.0 KB-8.0 KB]: 95377 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 4.1 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_TYPETREE_THREAD]
+      Peak usage frame count: [2.0 KB-4.0 KB]: 95377 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 2.6 KB
+      Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -0,0 +1,368 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 1.9859017133712769,
+            "min": 1.8782767057418823,
+            "max": 2.047666311264038,
+            "count": 503
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 43912.2578125,
+            "min": 26401.89453125,
+            "max": 57758.5703125,
+            "count": 503
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 131.0810810810811,
+            "min": 86.94736842105263,
+            "max": 289.3529411764706,
+            "count": 503
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19400.0,
+            "min": 11584.0,
+            "max": 22404.0,
+            "count": 503
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1355.888441358503,
+            "min": 1275.441077197799,
+            "max": 1395.6823735516607,
+            "count": 503
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 100335.74466052922,
+            "min": 46278.77371434013,
+            "max": 157519.3615876046,
+            "count": 503
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 19759814.0,
+            "min": 14739517.0,
+            "max": 19759814.0,
+            "count": 503
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 19759814.0,
+            "min": 14739517.0,
+            "max": 19759814.0,
+            "count": 503
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": 0.03069358877837658,
+            "min": -0.1309611052274704,
+            "max": 0.07966340333223343,
+            "count": 503
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": 2.2713255882263184,
+            "min": -9.1473388671875,
+            "max": 7.55604887008667,
+            "count": 503
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.031498800963163376,
+            "min": -0.13048842549324036,
+            "max": 0.08405119925737381,
+            "count": 503
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2.330911159515381,
+            "min": -9.151137351989746,
+            "max": 7.783769607543945,
+            "count": 503
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 503
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 503
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.19556216291479162,
+            "min": -0.495235821204399,
+            "max": 0.3988244874136789,
+            "count": 503
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -14.47160005569458,
+            "min": -37.217599987983704,
+            "max": 24.86560007929802,
+            "count": 503
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.19556216291479162,
+            "min": -0.495235821204399,
+            "max": 0.3988244874136789,
+            "count": 503
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -14.47160005569458,
+            "min": -37.217599987983704,
+            "max": 24.86560007929802,
+            "count": 503
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 503
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 503
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.06393893646309153,
+            "min": 0.03340033383501577,
+            "max": 0.06742940049734898,
+            "count": 242
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.06393893646309153,
+            "min": 0.03340033383501577,
+            "max": 0.06742940049734898,
+            "count": 242
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.041843350138515235,
+            "min": 0.027015811251476406,
+            "max": 0.0498456965200603,
+            "count": 242
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.041843350138515235,
+            "min": 0.027015811251476406,
+            "max": 0.0498456965200603,
+            "count": 242
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.042491350695490836,
+            "min": 0.027287230407819153,
+            "max": 0.11414098488166928,
+            "count": 242
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.042491350695490836,
+            "min": 0.027287230407819153,
+            "max": 0.11414098488166928,
+            "count": 242
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0006,
+            "min": 0.0006,
+            "max": 0.0006,
+            "count": 242
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0006,
+            "min": 0.0006,
+            "max": 0.0006,
+            "count": 242
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.25,
+            "min": 0.25,
+            "max": 0.25,
+            "count": 242
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.25,
+            "min": 0.25,
+            "max": 0.25,
+            "count": 242
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.01,
+            "min": 0.01,
+            "max": 0.01,
+            "count": 242
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.01,
+            "min": 0.01,
+            "max": 0.01,
+            "count": 242
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1694602557",
+        "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\\bdonn\\miniconda3\\envs\\DRL\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=../Soccer/Soccer.exe --run-id=SoccerTeamBest --no-graphics --resume",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.0.1",
+        "numpy_version": "1.25.2",
+        "end_time_seconds": "1694614705"
+    },
+    "total": 12148.1823553,
+    "count": 1,
+    "self": 0.009439400004339404,
+    "children": {
+        "run_training.setup": {
+            "total": 0.15632360000017798,
+            "count": 1,
+            "self": 0.15632360000017798
+        },
+        "TrainerController.start_learning": {
+            "total": 12148.016592299995,
+            "count": 1,
+            "self": 10.847635998863552,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 8.639452600000368,
+                    "count": 27,
+                    "self": 8.639452600000368
+                },
+                "TrainerController.advance": {
+                    "total": 12127.91326110113,
+                    "count": 331597,
+                    "self": 8.829515205186908,
+                    "children": {
+                        "env_step": {
+                            "total": 8470.883554400643,
+                            "count": 331597,
+                            "self": 5137.614543701704,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 3326.408375000523,
+                                    "count": 331597,
+                                    "self": 66.59249130216631,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 3259.8158836983566,
+                                            "count": 635860,
+                                            "self": 3259.8158836983566
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 6.860635698416445,
+                                    "count": 331596,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 12127.36054439786,
+                                            "count": 331596,
+                                            "is_parallel": true,
+                                            "self": 8209.646047699476,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.05584750002162764,
+                                                    "count": 54,
+                                                    "is_parallel": true,
+                                                    "self": 0.0095781999771134,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.04626930004451424,
+                                                            "count": 216,
+                                                            "is_parallel": true,
+                                                            "self": 0.04626930004451424
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 3917.6586491983617,
+                                                    "count": 331596,
+                                                    "is_parallel": true,
+                                                    "self": 192.37256239513954,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 176.07630829917616,
+                                                            "count": 331596,
+                                                            "is_parallel": true,
+                                                            "self": 176.07630829917616
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 2872.249153202618,
+                                                            "count": 331596,
+                                                            "is_parallel": true,
+                                                            "self": 2872.249153202618
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 676.9606253014281,
+                                                            "count": 663192,
+                                                            "is_parallel": true,
+                                                            "self": 115.5395211017094,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 561.4211041997187,
+                                                                    "count": 2652768,
+                                                                    "is_parallel": true,
+                                                                    "self": 561.4211041997187
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 3648.2001914953,
+                            "count": 331596,
+                            "self": 82.72545919418917,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 999.1311738010991,
+                                    "count": 331596,
+                                    "self": 993.645664301097,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 5.485509500002081,
+                                            "count": 10,
+                                            "self": 5.485509500002081
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 2566.3435585000116,
+                                    "count": 242,
+                                    "self": 1317.0311211999579,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 1249.3124373000537,
+                                            "count": 9680,
+                                            "self": 1249.3124373000537
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.3999961083754897e-06,
+                    "count": 1,
+                    "self": 1.3999961083754897e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.6162412000048789,
+                    "count": 1,
+                    "self": 0.016175400007341523,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.6000657999975374,
+                            "count": 1,
+                            "self": 0.6000657999975374
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 17999734,
+                "file_path": "results\\SoccerTeamBest\\SoccerTwos\\SoccerTwos-17999734.onnx",
+                "reward": 0.0,
+                "creation_time": 1694610380.4909735,
+                "auxillary_file_paths": [
+                    "results\\SoccerTeamBest\\SoccerTwos\\SoccerTwos-17999734.pt"
+                ]
+            },
+            {
+                "steps": 18499770,
+                "file_path": "results\\SoccerTeamBest\\SoccerTwos\\SoccerTwos-18499770.onnx",
+                "reward": 0.0,
+                "creation_time": 1694611579.1615715,
+                "auxillary_file_paths": [
+                    "results\\SoccerTeamBest\\SoccerTwos\\SoccerTwos-18499770.pt"
+                ]
+            },
+            {
+                "steps": 18999904,
+                "file_path": "results\\SoccerTeamBest\\SoccerTwos\\SoccerTwos-18999904.onnx",
+                "reward": 0.0,
+                "creation_time": 1694612808.2102637,
+                "auxillary_file_paths": [
+                    "results\\SoccerTeamBest\\SoccerTwos\\SoccerTwos-18999904.pt"
+                ]
+            },
+            {
+                "steps": 19499952,
+                "file_path": "results\\SoccerTeamBest\\SoccerTwos\\SoccerTwos-19499952.onnx",
+                "reward": 0.0,
+                "creation_time": 1694614049.6798658,
+                "auxillary_file_paths": [
+                    "results\\SoccerTeamBest\\SoccerTwos\\SoccerTwos-19499952.pt"
+                ]
+            },
+            {
+                "steps": 19769974,
+                "file_path": "results\\SoccerTeamBest\\SoccerTwos\\SoccerTwos-19769974.onnx",
+                "reward": 0.0,
+                "creation_time": 1694614705.1744304,
+                "auxillary_file_paths": [
+                    "results\\SoccerTeamBest\\SoccerTwos\\SoccerTwos-19769974.pt"
+                ]
+            }
+        ],
+        "elo": 1351.0258993510174,
+        "final_checkpoint": {
+            "steps": 19769974,
+            "file_path": "results\\SoccerTeamBest\\SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1694614705.1744304,
+            "auxillary_file_paths": [
+                "results\\SoccerTeamBest\\SoccerTwos\\SoccerTwos-19769974.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "2.0.1"
+    }
+}