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: MartinRedWhite/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 sha256:59e9f459bfdf0e59aa3cfbbc192b6c32f37203a6522c053d523cd8b5d6d5dd75
+size 1768747

SoccerTwos/SoccerTwos-32499645.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:265c5c45b23cb827eb1dd8f999eed64d6c5ccad268817f874553cfe31e072bfe
+size 1768747

SoccerTwos/SoccerTwos-32499645.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feeebc2553adf94e288b2e7934b9407e334d8f54cf849ce125160fea19e09829
+size 28432146

SoccerTwos/SoccerTwos-32999974.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8c15954005994db391e071c840c6792d72d217fbe4fae39db67b0dcfeef59c3
+size 1768747

SoccerTwos/SoccerTwos-32999974.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92d142f60d6066df2fc7b219127093e9f31e666b8002fc2d795a166ff94e0902
+size 28432146

SoccerTwos/SoccerTwos-33499949.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:951e707896a5bc16893c7c05235e73a88dbbd0750382196dcb0b4f91ed55336a
+size 1768747

SoccerTwos/SoccerTwos-33499949.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ad9c91fc04ebc9b1eabb54fb5389219cfc90f90b975527722163ad37b6f355c
+size 28432146

SoccerTwos/SoccerTwos-33999988.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:606771e12ced5fe1ec14e5339ef18300fea23521fb053caa60db2832955c955c
+size 1768747

SoccerTwos/SoccerTwos-33999988.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bab51e9d3e2ee316ce64d3adbb7c0516788855fa9c1dbf4460fd234344b0a01a
+size 28432146

SoccerTwos/SoccerTwos-48499992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5e617042521af14f68661fe2fe0bf70252873120c834147efe21023057ec20e
+size 1768747

SoccerTwos/SoccerTwos-48499992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c94c13939f78a8484b711ab1bd5c8b518004e6df3e3c9992a38461a62b26bf8
+size 28432146

SoccerTwos/SoccerTwos-48999920.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:745eaaffb1163547a8e72963f5b47726e46bb9d168ef3fd7e8c18a9080751f66
+size 1768747

SoccerTwos/SoccerTwos-48999920.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb2b71c1bdd3a587101e011ffc4bc4c413c5d45a11643a9bf9c8279314b8338f
+size 28432146

SoccerTwos/SoccerTwos-49499794.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afdd176cfb8d9918419444000cf2a627cb3d9d7819e35f2a1367e00d78c883d0
+size 1768747

SoccerTwos/SoccerTwos-49499794.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a2375694cb48df001ea73b781df92f5d7db5a78ed782c28b44178d4a23234ec
+size 28432146

SoccerTwos/SoccerTwos-49999938.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59e9f459bfdf0e59aa3cfbbc192b6c32f37203a6522c053d523cd8b5d6d5dd75
+size 1768747

SoccerTwos/SoccerTwos-49999938.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f728ccf49f67d36bf2aaceee4a20e905559a06591ffebbd382ed6e0cd661390
+size 28432146

SoccerTwos/SoccerTwos-50000054.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59e9f459bfdf0e59aa3cfbbc192b6c32f37203a6522c053d523cd8b5d6d5dd75
+size 1768747

SoccerTwos/SoccerTwos-50000054.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35e154f98aae8d062dd31bc8d6379866567bc3ef612bee8ac2bf9a2a06c7b02a
+size 28432146

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c090949786bb9d868c298e27130892ebd4aa26b165c95179a8035788dfd3c84
+size 28431030

SoccerTwos/events.out.tfevents.1739556451.martin-legion.136093.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f472c1cf98203d9be0c4e28adb0a4121d3370d082f07a46ac4aa4c612934105b
+size 34742272

SoccerTwos/events.out.tfevents.1739630703.martin-legion.5573.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36a1ef3383419a1499bbbc217027c0dc42e9c26f1e5253934003f28c0e0d815c
+size 15932109

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 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": 50000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "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 +1,84 @@
+default_settings: null
+behaviors:
+  SoccerTwos:
+    trainer_type: poca
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: constant
+      beta_schedule: constant
+      epsilon_schedule: constant
+    checkpoint_interval: 500000
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 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: 50000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 50000
+      team_change: 200000
+      swap_steps: 2000
+      window: 10
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/SoccerTwos.x86_64
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  timeout_wait: 60
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: SoccerTwos
+  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 +1,304 @@
+Mono path[0] = '/home/data/rl_training_hugging_face/ml-agents/training-envs-executables/SoccerTwos_Data/Managed'
+Mono config path = '/home/data/rl_training_hugging_face/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/data/rl_training_hugging_face/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  0.544 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: 0.898089 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
+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]: 291751 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 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 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 0.7 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 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]: 291752 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 4.8 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 291752 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.5 MB
+      Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 291751 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]: 291752 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]: 291752 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]: 291751 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]: 291752 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]: 291751 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": 1.3858288526535034,
+            "min": 1.2831696271896362,
+            "max": 1.5118088722229004,
+            "count": 1551
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 27583.537109375,
+            "min": 459.28411865234375,
+            "max": 36137.79296875,
+            "count": 1551
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 69.46478873239437,
+            "min": 9.0,
+            "max": 96.6470588235294,
+            "count": 1551
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19728.0,
+            "min": 36.0,
+            "max": 21096.0,
+            "count": 1551
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1156.7548752227067,
+            "min": 1121.9605773855733,
+            "max": 1215.9710910151005,
+            "count": 1551
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 164259.19228162436,
+            "min": 2400.0,
+            "max": 265511.6147403742,
+            "count": 1551
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 1551
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 1551
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 49999938.0,
+            "min": 34509994.0,
+            "max": 49999938.0,
+            "count": 1550
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 49999938.0,
+            "min": 34509994.0,
+            "max": 49999938.0,
+            "count": 1550
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": 0.004603617824614048,
+            "min": -0.12251940369606018,
+            "max": 0.08070683479309082,
+            "count": 1550
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": 0.6537137031555176,
+            "min": -19.88117790222168,
+            "max": 13.074506759643555,
+            "count": 1550
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.0075112516060471535,
+            "min": -0.12653417885303497,
+            "max": 0.08202705532312393,
+            "count": 1550
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 1.0665977001190186,
+            "min": -19.612796783447266,
+            "max": 13.288383483886719,
+            "count": 1550
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 1550
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 1550
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.06413098498129509,
+            "min": -0.458425479330075,
+            "max": 0.32652919336875774,
+            "count": 1550
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 9.106599867343903,
+            "min": -71.97280025482178,
+            "max": 52.571200132369995,
+            "count": 1550
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.06413098498129509,
+            "min": -0.458425479330075,
+            "max": 0.32652919336875774,
+            "count": 1550
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 9.106599867343903,
+            "min": -71.97280025482178,
+            "max": 52.571200132369995,
+            "count": 1550
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.017318676091963425,
+            "min": 0.010963460166628162,
+            "max": 0.025687383694457822,
+            "count": 752
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.017318676091963425,
+            "min": 0.010963460166628162,
+            "max": 0.025687383694457822,
+            "count": 752
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.08368794247508049,
+            "min": 0.07948353836933772,
+            "max": 0.12492935384313265,
+            "count": 752
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.08368794247508049,
+            "min": 0.07948353836933772,
+            "max": 0.12492935384313265,
+            "count": 752
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.08451702346404394,
+            "min": 0.08034255852301915,
+            "max": 0.12692295461893083,
+            "count": 752
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.08451702346404394,
+            "min": 0.08034255852301915,
+            "max": 0.12692295461893083,
+            "count": 752
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 752
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 752
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 752
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 752
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 752
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 752
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1739630700",
+        "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
+        "command_line_arguments": "/home/martin/.conda/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.6.0+cu124",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1739653520"
+    },
+    "total": 22820.236690822003,
+    "count": 1,
+    "self": 0.7163401410034567,
+    "children": {
+        "run_training.setup": {
+            "total": 0.025145049000002473,
+            "count": 1,
+            "self": 0.025145049000002473
+        },
+        "TrainerController.start_learning": {
+            "total": 22819.495205632,
+            "count": 1,
+            "self": 18.463301170897466,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 6.6275137489827785,
+                    "count": 79,
+                    "self": 6.6275137489827785
+                },
+                "TrainerController.advance": {
+                    "total": 22794.19891282612,
+                    "count": 1066530,
+                    "self": 18.084316897984536,
+                    "children": {
+                        "env_step": {
+                            "total": 17174.28582676853,
+                            "count": 1066530,
+                            "self": 12402.562278144578,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 4760.794284539471,
+                                    "count": 1066530,
+                                    "self": 95.51397966927925,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 4665.280304870192,
+                                            "count": 1945040,
+                                            "self": 4665.280304870192
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 10.929264084480849,
+                                    "count": 1066530,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 22793.238753897935,
+                                            "count": 1066530,
+                                            "is_parallel": true,
+                                            "self": 12350.73444080167,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.010124259999997776,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.00866584399994963,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.001458416000048146,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.001458416000048146
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.021964351000008264,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005095200000369005,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0003623360000233333,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003623360000233333
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.01967566899998019,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.01967566899998019
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0014168259999678412,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00034008999995194245,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0010767360000158988,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0010767360000158988
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.11035080202765357,
+                                                    "count": 156,
+                                                    "is_parallel": true,
+                                                    "self": 0.021050113038370455,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.08930068898928312,
+                                                            "count": 624,
+                                                            "is_parallel": true,
+                                                            "self": 0.08930068898928312
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 10442.393962294236,
+                                                    "count": 1066529,
+                                                    "is_parallel": true,
+                                                    "self": 471.81837299668405,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 300.1230294600172,
+                                                            "count": 1066529,
+                                                            "is_parallel": true,
+                                                            "self": 300.1230294600172
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 8237.211792437312,
+                                                            "count": 1066529,
+                                                            "is_parallel": true,
+                                                            "self": 8237.211792437312
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 1433.2407674002218,
+                                                            "count": 2133058,
+                                                            "is_parallel": true,
+                                                            "self": 275.6788877206154,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 1157.5618796796064,
+                                                                    "count": 8532232,
+                                                                    "is_parallel": true,
+                                                                    "self": 1157.5618796796064
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 5601.828769159603,
+                            "count": 1066530,
+                            "self": 118.19624943426606,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 2553.2714778033155,
+                                    "count": 1066530,
+                                    "self": 2548.8034817663147,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 4.467996037000603,
+                                            "count": 32,
+                                            "self": 4.467996037000603
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 2930.361041922022,
+                                    "count": 752,
+                                    "self": 1434.506449910947,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 1495.8545920110753,
+                                            "count": 22560,
+                                            "self": 1495.8545920110753
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 6.810005288571119e-07,
+                    "count": 1,
+                    "self": 6.810005288571119e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.20547720499962452,
+                    "count": 1,
+                    "self": 0.0009686499979579821,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.20450855500166654,
+                            "count": 1,
+                            "self": 0.20450855500166654
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 48499992,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-48499992.onnx",
+                "reward": 0.0,
+                "creation_time": 1739651361.6132364,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-48499992.pt"
+                ]
+            },
+            {
+                "steps": 48999920,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-48999920.onnx",
+                "reward": 0.0,
+                "creation_time": 1739652086.9635873,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-48999920.pt"
+                ]
+            },
+            {
+                "steps": 49499794,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-49499794.onnx",
+                "reward": 0.0,
+                "creation_time": 1739652803.6047711,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-49499794.pt"
+                ]
+            },
+            {
+                "steps": 49999938,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-49999938.onnx",
+                "reward": 0.0,
+                "creation_time": 1739653519.7554255,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-49999938.pt"
+                ]
+            },
+            {
+                "steps": 50000054,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-50000054.onnx",
+                "reward": 0.0,
+                "creation_time": 1739653519.9745276,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-50000054.pt"
+                ]
+            }
+        ],
+        "elo": 1155.111609836932,
+        "final_checkpoint": {
+            "steps": 50000054,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1739653519.9745276,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-50000054.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.6.0+cu124"
+    }
+}