ELO of 1760+

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: saxelsso/poca-SoccerTwos-best
+  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:f272789f62384b28919a5ba5f11185bc878cc8218aa18749ab66f95c9366f678
+size 2820313

SoccerTwos/SoccerTwos-18499995.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:181868734bacfcbdf3d67e2829a3b6499fb5c7ca7c5a3c358961be3fbab94db0
+size 2820313

SoccerTwos/SoccerTwos-18499995.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b470320e98f2f223ef1db22d296251d51edb818d274026275a4f2908f43500a
+size 34741042

SoccerTwos/SoccerTwos-18999934.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ce4414425119547bfdd133266358e9ae131e9148ccc43037ab4bb6627b4b64c
+size 2820313

SoccerTwos/SoccerTwos-18999934.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:310429f7230cf3cd5f98c4f04e310cfd6031c40dd8be0fe1e90bd3c07096dd7f
+size 34741042

SoccerTwos/SoccerTwos-19499932.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2415ba7fb5ec91aaf820afe45946a391a52ce27af87f13b47a91571efb319f36
+size 2820313

SoccerTwos/SoccerTwos-19499932.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:807de6fe78b02150a222c70b07567e518efd140437eace5a95c02960c58100ef
+size 34741042

SoccerTwos/SoccerTwos-19999944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f272789f62384b28919a5ba5f11185bc878cc8218aa18749ab66f95c9366f678
+size 2820313

SoccerTwos/SoccerTwos-19999944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d7ee03e61aadd95b04cb8e33f4a6fbe35ec875035c754c67981cb314a985015
+size 34741042

SoccerTwos/SoccerTwos-20000150.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f272789f62384b28919a5ba5f11185bc878cc8218aa18749ab66f95c9366f678
+size 2820313

SoccerTwos/SoccerTwos-20000150.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4033f99c5115c8f959bb01304ff47a8d5f57f503506190f2931f3d8bd6d3a582
+size 34741042

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f50f8ee2bb1035cd0a2b7c61830c4fbb270e57d42e2846a0a3efc43acdd75d51
+size 34739782

SoccerTwos/events.out.tfevents.1736525133.RYZEN.1725872.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7832f8a0bb5793ba8832ebed85c2be087b2a4e88e5003b578be77ff12908b9b2
+size 20494782

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": 5, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 20000000, "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/SoccerTwos", "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": "SoccerTwos9", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": "cuda"}, "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: 5
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 500000
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 3
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+    init_path: null
+    keep_checkpoints: 5
+    even_checkpoints: false
+    max_steps: 20000000
+    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/SoccerTwos
+  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: SoccerTwos9
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: cuda
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,566 @@
+Mono path[0] = '/home/stefan/src/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = '/home/stefan/src/ml-agents/training-envs-executables/SoccerTwos/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/stefan/src/ml-agents/training-envs-executables/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  0.045 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: 0.517954 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+requesting resize 84 x 84
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+Setting up 16 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]: 376648 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_Job.Worker 18]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 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_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_Job.Worker 16]
+      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 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 27]
+      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 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 17]
+      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_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_AssetGarbageCollectorHelper] x 31
+      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_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_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 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 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 20]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 11]
+      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 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_TEMP_Job.Worker 30]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 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_Job.Worker 21]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 26]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 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_Job.Worker 25]
+      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 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 29]
+      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 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 16
+      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 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 28]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 22]
+      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 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 9]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_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 23]
+      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 0.7 KB
+      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_Job.Worker 24]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 15]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 19]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 12]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      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_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 5
+    [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]: 376649 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 4.7 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 376649 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]: 376648 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]: 376649 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]: 376649 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]: 376648 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]: 376649 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]: 376648 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": 0.7494909167289734,
+            "min": 0.7274272441864014,
+            "max": 3.295811891555786,
+            "count": 2000
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 14797.94921875,
+            "min": 12973.8681640625,
+            "max": 105465.96875,
+            "count": 2000
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 59.83132530120482,
+            "min": 45.5188679245283,
+            "max": 999.0,
+            "count": 2000
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19864.0,
+            "min": 14736.0,
+            "max": 25268.0,
+            "count": 2000
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1761.490137084402,
+            "min": 1195.844794550754,
+            "max": 1800.3034901610533,
+            "count": 1998
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 292407.3627560107,
+            "min": 2399.4985597382833,
+            "max": 378386.4566191012,
+            "count": 1998
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 19999944.0,
+            "min": 9652.0,
+            "max": 19999944.0,
+            "count": 2000
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 19999944.0,
+            "min": 9652.0,
+            "max": 19999944.0,
+            "count": 2000
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.03484977036714554,
+            "min": -0.13655488193035126,
+            "max": 0.18776509165763855,
+            "count": 2000
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -5.7502121925354,
+            "min": -19.800457000732422,
+            "max": 24.784992218017578,
+            "count": 2000
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.03535076603293419,
+            "min": -0.1446973830461502,
+            "max": 0.18393611907958984,
+            "count": 2000
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -5.832876682281494,
+            "min": -20.981121063232422,
+            "max": 24.25238800048828,
+            "count": 2000
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 2000
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 2000
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.09759272842696219,
+            "min": -0.6470588235294118,
+            "max": 0.6544881351923538,
+            "count": 2000
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -16.10280019044876,
+            "min": -57.34900003671646,
+            "max": 61.02780032157898,
+            "count": 2000
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.09759272842696219,
+            "min": -0.6470588235294118,
+            "max": 0.6544881351923538,
+            "count": 2000
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -16.10280019044876,
+            "min": -57.34900003671646,
+            "max": 61.02780032157898,
+            "count": 2000
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 2000
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 2000
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.018186160400509833,
+            "min": 0.011413839999950142,
+            "max": 0.023963280958123504,
+            "count": 970
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.018186160400509833,
+            "min": 0.011413839999950142,
+            "max": 0.023963280958123504,
+            "count": 970
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.1014073920249939,
+            "min": 0.0006905387435108423,
+            "max": 0.12033649995923042,
+            "count": 970
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.1014073920249939,
+            "min": 0.0006905387435108423,
+            "max": 0.12033649995923042,
+            "count": 970
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.10152057856321335,
+            "min": 0.0007671873888466507,
+            "max": 0.1208409234881401,
+            "count": 970
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.10152057856321335,
+            "min": 0.0007671873888466507,
+            "max": 0.1208409234881401,
+            "count": 970
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 5.8869980410007976e-08,
+            "min": 5.8869980410007976e-08,
+            "max": 0.00029969238010254,
+            "count": 970
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 5.8869980410007976e-08,
+            "min": 5.8869980410007976e-08,
+            "max": 0.00029969238010254,
+            "count": 970
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.10001958999999999,
+            "min": 0.10001958999999999,
+            "max": 0.19989746000000008,
+            "count": 970
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.10001958999999999,
+            "min": 0.10001958999999999,
+            "max": 0.19989746000000008,
+            "count": 970
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 1.0977541000000134e-05,
+            "min": 1.0977541000000134e-05,
+            "max": 0.004994883254,
+            "count": 970
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 1.0977541000000134e-05,
+            "min": 1.0977541000000134e-05,
+            "max": 0.004994883254,
+            "count": 970
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1736525133",
+        "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
+        "command_line_arguments": "/home/stefan/miniconda3/envs/ml-agents/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos --run-id=SoccerTwos9 --no-graphics --torch-device cuda",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.5.1+cu124",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1736560686"
+    },
+    "total": 35553.45176794598,
+    "count": 1,
+    "self": 0.36873860395280644,
+    "children": {
+        "run_training.setup": {
+            "total": 0.010447545006172732,
+            "count": 1,
+            "self": 0.010447545006172732
+        },
+        "TrainerController.start_learning": {
+            "total": 35553.07258179702,
+            "count": 1,
+            "self": 20.50890109487227,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.5408188490837347,
+                    "count": 100,
+                    "self": 2.5408188490837347
+                },
+                "TrainerController.advance": {
+                    "total": 35529.84262374806,
+                    "count": 1373369,
+                    "self": 18.59447276283754,
+                    "children": {
+                        "env_step": {
+                            "total": 25630.410534975643,
+                            "count": 1373369,
+                            "self": 15407.643253953662,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 10210.252099557867,
+                                    "count": 1373369,
+                                    "self": 119.48115686824895,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 10090.770942689618,
+                                            "count": 2511022,
+                                            "self": 10090.770942689618
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 12.515181464113994,
+                                    "count": 1373369,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 35511.73678986286,
+                                            "count": 1373369,
+                                            "is_parallel": true,
+                                            "self": 22254.38950994931,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.001703521003946662,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.0004977550415787846,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0012057659623678774,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0012057659623678774
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.01932847499847412,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00047046400140970945,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0003157659957651049,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003157659957651049
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.01738781700260006,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.01738781700260006
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0011544279986992478,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0002629169903229922,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0008915110083762556,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0008915110083762556
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 13257.236389755388,
+                                                    "count": 1373368,
+                                                    "is_parallel": true,
+                                                    "self": 444.57447525358293,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 298.1148695660231,
+                                                            "count": 1373368,
+                                                            "is_parallel": true,
+                                                            "self": 298.1148695660231
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 11122.894891028845,
+                                                            "count": 1373368,
+                                                            "is_parallel": true,
+                                                            "self": 11122.894891028845
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 1391.6521539069363,
+                                                            "count": 2746736,
+                                                            "is_parallel": true,
+                                                            "self": 302.3874715605052,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 1089.264682346431,
+                                                                    "count": 10986944,
+                                                                    "is_parallel": true,
+                                                                    "self": 1089.264682346431
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.1108901581610553,
+                                                    "count": 198,
+                                                    "is_parallel": true,
+                                                    "self": 0.025228983722627163,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.08566117443842813,
+                                                            "count": 792,
+                                                            "is_parallel": true,
+                                                            "self": 0.08566117443842813
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 9880.83761600958,
+                            "count": 1373369,
+                            "self": 158.14742665737867,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 4639.92850754768,
+                                    "count": 1373369,
+                                    "self": 4632.432310309639,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 7.496197238040622,
+                                            "count": 40,
+                                            "self": 7.496197238040622
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 5082.761681804521,
+                                    "count": 970,
+                                    "self": 2451.060621449986,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 2631.701060354535,
+                                            "count": 48505,
+                                            "self": 2631.701060354535
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 8.399947546422482e-07,
+                    "count": 1,
+                    "self": 8.399947546422482e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.18023726501269266,
+                    "count": 1,
+                    "self": 0.0019373390241526067,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.17829992598854005,
+                            "count": 1,
+                            "self": 0.17829992598854005
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 18499995,
+                "file_path": "results/SoccerTwos9/SoccerTwos/SoccerTwos-18499995.onnx",
+                "reward": 0.0,
+                "creation_time": 1736557976.9825761,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos9/SoccerTwos/SoccerTwos-18499995.pt"
+                ]
+            },
+            {
+                "steps": 18999934,
+                "file_path": "results/SoccerTwos9/SoccerTwos/SoccerTwos-18999934.onnx",
+                "reward": 0.0,
+                "creation_time": 1736558870.9530761,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos9/SoccerTwos/SoccerTwos-18999934.pt"
+                ]
+            },
+            {
+                "steps": 19499932,
+                "file_path": "results/SoccerTwos9/SoccerTwos/SoccerTwos-19499932.onnx",
+                "reward": 0.0,
+                "creation_time": 1736559769.5828886,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos9/SoccerTwos/SoccerTwos-19499932.pt"
+                ]
+            },
+            {
+                "steps": 19999944,
+                "file_path": "results/SoccerTwos9/SoccerTwos/SoccerTwos-19999944.onnx",
+                "reward": 0.0,
+                "creation_time": 1736560685.9080791,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos9/SoccerTwos/SoccerTwos-19999944.pt"
+                ]
+            },
+            {
+                "steps": 20000150,
+                "file_path": "results/SoccerTwos9/SoccerTwos/SoccerTwos-20000150.onnx",
+                "reward": 0.0,
+                "creation_time": 1736560686.1292286,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos9/SoccerTwos/SoccerTwos-20000150.pt"
+                ]
+            }
+        ],
+        "elo": 1765.0175806969903,
+        "final_checkpoint": {
+            "steps": 20000150,
+            "file_path": "results/SoccerTwos9/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1736560686.1292286,
+            "auxillary_file_paths": [
+                "results/SoccerTwos9/SoccerTwos/SoccerTwos-20000150.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.5.1+cu124"
+    }
+}