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: Stoub/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 sha256:6bbcbec495b07bb7e1cb23ecc71b8d6a5c2c6b72290059a6ade170c493c5a32d
+size 1768747

SoccerTwos/SoccerTwos-3499868.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:533a4e8b24b8806e8b89afdf56b469ef537503bb9e7124859ea4b587cd8f63a7
+size 1768747

SoccerTwos/SoccerTwos-3499868.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8568208cb439ec003342c931fc512f0454dd234fd1ca79a13d4e4b9ed38617ee
+size 28430358

SoccerTwos/SoccerTwos-3999944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e29032966738007c1f9e65a0c43fe1da58ccd48cadc86b8f6c2e3dd93069e1a
+size 1768747

SoccerTwos/SoccerTwos-3999944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:685935aed9a481115593e0c39a1fd895c64599358a837889d88f857a49fa136d
+size 28430358

SoccerTwos/SoccerTwos-4499948.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c5e97a2cb385119b7f32f15603ec378f5dda49326e64d1c9ef5362fed1d4430
+size 1768747

SoccerTwos/SoccerTwos-4499948.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d583ce70c2ceae55e029d9697b0e1909b51d2839a6350e49e94ce7bc928f034
+size 28430358

SoccerTwos/SoccerTwos-4999996.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bbcbec495b07bb7e1cb23ecc71b8d6a5c2c6b72290059a6ade170c493c5a32d
+size 1768747

SoccerTwos/SoccerTwos-4999996.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aca3f3555b5555ac0d7ef784b6bf4702c1becce1e48b8edd293055a0c0ff53b
+size 28430358

SoccerTwos/SoccerTwos-5000032.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bbcbec495b07bb7e1cb23ecc71b8d6a5c2c6b72290059a6ade170c493c5a32d
+size 1768747

SoccerTwos/SoccerTwos-5000032.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89291dbb0952edab6fccfd359af75c64128d480fe65dcb737d50f9506c32e334
+size 28430358

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cd35da20bde75724dffe0297fef0776b469fdd0f0d373aba24e2e7b8830a769
+size 28429366

SoccerTwos/events.out.tfevents.1727369592.ca53010d331d.741.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:878ca7b9d89d6b1e546339f05fbec6fc5f4f6b63155ea0cdee77b5b231fa4838
+size 4885050

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": 5000000, "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/linux/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": false, "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: 5000000
+    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/linux/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: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,698 @@
+Mono path[0] = '/home/ml-agents/training-envs-executables/linux/SoccerTwos_Data/Managed'
+Mono config path = '/home/ml-agents/training-envs-executables/linux/SoccerTwos_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
+PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/SoccerTwos
+Unable to load player prefs
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /home/ml-agents/training-envs-executables/linux/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
+FMOD initialized on nosound output
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.074 seconds
+ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard (Specular setup)' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Standard (Specular setup) shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard (Specular setup)' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'Standard' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+UnloadTime: 0.643659 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+requesting resize 84 x 84
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+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 2 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]: 94756 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_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 0]
+      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 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 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_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 2
+      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 3
+      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_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_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]: 94757 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 4.9 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 94757 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.4 MB
+      Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 94756 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]: 94757 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]: 94757 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]: 94756 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]: 94757 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]: 94756 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": 2.060180902481079,
+            "min": 2.0366084575653076,
+            "max": 3.2957489490509033,
+            "count": 500
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 37775.4765625,
+            "min": 25640.1796875,
+            "max": 124540.796875,
+            "count": 500
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 64.23684210526316,
+            "min": 43.41228070175438,
+            "max": 999.0,
+            "count": 500
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19528.0,
+            "min": 16252.0,
+            "max": 23688.0,
+            "count": 500
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1568.1828422437923,
+            "min": 1184.8733249128697,
+            "max": 1591.4549585676755,
+            "count": 490
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 238363.79202105643,
+            "min": 2369.7466498257395,
+            "max": 354290.0691976056,
+            "count": 490
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 4999996.0,
+            "min": 9488.0,
+            "max": 4999996.0,
+            "count": 500
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 4999996.0,
+            "min": 9488.0,
+            "max": 4999996.0,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.022454505786299706,
+            "min": -0.08605106920003891,
+            "max": 0.17248587310314178,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -3.4355392456054688,
+            "min": -16.349702835083008,
+            "max": 21.856319427490234,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.024616263806819916,
+            "min": -0.08110318332910538,
+            "max": 0.16757957637310028,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -3.7662882804870605,
+            "min": -15.08519172668457,
+            "max": 22.9644718170166,
+            "count": 500
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 500
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.054274510713963726,
+            "min": -0.5384615384615384,
+            "max": 0.37619402426392284,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -8.30400013923645,
+            "min": -54.3367999792099,
+            "max": 61.355800092220306,
+            "count": 500
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.054274510713963726,
+            "min": -0.5384615384615384,
+            "max": 0.37619402426392284,
+            "count": 500
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -8.30400013923645,
+            "min": -54.3367999792099,
+            "max": 61.355800092220306,
+            "count": 500
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 500
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 500
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.012937161442823707,
+            "min": 0.010601800406584516,
+            "max": 0.023501068291564783,
+            "count": 240
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.012937161442823707,
+            "min": 0.010601800406584516,
+            "max": 0.023501068291564783,
+            "count": 240
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.10735289230942727,
+            "min": 0.00017051689076955274,
+            "max": 0.11434300442536673,
+            "count": 240
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.10735289230942727,
+            "min": 0.00017051689076955274,
+            "max": 0.11434300442536673,
+            "count": 240
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.1099305289487044,
+            "min": 0.0001683511588150092,
+            "max": 0.11686786686380704,
+            "count": 240
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.1099305289487044,
+            "min": 0.0001683511588150092,
+            "max": 0.11686786686380704,
+            "count": 240
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 240
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 240
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.2,
+            "max": 0.20000000000000007,
+            "count": 240
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.2,
+            "max": 0.20000000000000007,
+            "count": 240
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005,
+            "max": 0.005000000000000001,
+            "count": 240
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005,
+            "max": 0.005000000000000001,
+            "count": 240
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1727369591",
+        "python_version": "3.10.12 (main, Aug 16 2023, 05:39:07) [GCC 12.2.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.4.1+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1727388678"
+    },
+    "total": 19087.34006651299,
+    "count": 1,
+    "self": 0.27230525598861277,
+    "children": {
+        "run_training.setup": {
+            "total": 0.02452742398600094,
+            "count": 1,
+            "self": 0.02452742398600094
+        },
+        "TrainerController.start_learning": {
+            "total": 19087.043233833014,
+            "count": 1,
+            "self": 9.329972284089308,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.7176319319405593,
+                    "count": 25,
+                    "self": 2.7176319319405593
+                },
+                "TrainerController.advance": {
+                    "total": 19074.795949301973,
+                    "count": 339797,
+                    "self": 9.569373899052152,
+                    "children": {
+                        "env_step": {
+                            "total": 7215.81410285164,
+                            "count": 339797,
+                            "self": 5645.826248357742,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 1564.5003681878443,
+                                    "count": 339797,
+                                    "self": 58.23159076765296,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 1506.2687774201913,
+                                            "count": 631724,
+                                            "self": 1506.2687774201913
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 5.487486306054052,
+                                    "count": 339797,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 19073.511663525744,
+                                            "count": 339797,
+                                            "is_parallel": true,
+                                            "self": 14493.58961916584,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0033430790062993765,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.0014058079686947167,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0019372710376046598,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0019372710376046598
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.022890007006935775,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005640779854729772,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0005011320172343403,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0005011320172343403
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.020044882025104016,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.020044882025104016
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0017799149791244417,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004491359868552536,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0013307789922691882,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0013307789922691882
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 4579.874745954963,
+                                                    "count": 339796,
+                                                    "is_parallel": true,
+                                                    "self": 271.2976286878402,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 216.71171673206845,
+                                                            "count": 339796,
+                                                            "is_parallel": true,
+                                                            "self": 216.71171673206845
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 3261.8513107775652,
+                                                            "count": 339796,
+                                                            "is_parallel": true,
+                                                            "self": 3261.8513107775652
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 830.0140897574893,
+                                                            "count": 679592,
+                                                            "is_parallel": true,
+                                                            "self": 166.4034510877682,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 663.6106386697211,
+                                                                    "count": 2718368,
+                                                                    "is_parallel": true,
+                                                                    "self": 663.6106386697211
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.04729840494110249,
+                                                    "count": 48,
+                                                    "is_parallel": true,
+                                                    "self": 0.009920554468408227,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.03737785047269426,
+                                                            "count": 192,
+                                                            "is_parallel": true,
+                                                            "self": 0.03737785047269426
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 11849.412472551281,
+                            "count": 339797,
+                            "self": 67.42974598979345,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 1605.39068581225,
+                                    "count": 339797,
+                                    "self": 1603.2557784811943,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 2.1349073310557287,
+                                            "count": 10,
+                                            "self": 2.1349073310557287
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 10176.592040749238,
+                                    "count": 240,
+                                    "self": 823.4263972544286,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 9353.165643494809,
+                                            "count": 7203,
+                                            "self": 9353.165643494809
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.381005859002471e-06,
+                    "count": 1,
+                    "self": 1.381005859002471e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.19967893400462344,
+                    "count": 1,
+                    "self": 0.001612991007277742,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.1980659429973457,
+                            "count": 1,
+                            "self": 0.1980659429973457
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 3499868,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3499868.onnx",
+                "reward": 0.0,
+                "creation_time": 1727383095.8285344,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-3499868.pt"
+                ]
+            },
+            {
+                "steps": 3999944,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3999944.onnx",
+                "reward": 0.0,
+                "creation_time": 1727385004.0034707,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-3999944.pt"
+                ]
+            },
+            {
+                "steps": 4499948,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-4499948.onnx",
+                "reward": 0.0,
+                "creation_time": 1727386850.936313,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-4499948.pt"
+                ]
+            },
+            {
+                "steps": 4999996,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-4999996.onnx",
+                "reward": 0.0,
+                "creation_time": 1727388678.382225,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-4999996.pt"
+                ]
+            },
+            {
+                "steps": 5000032,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-5000032.onnx",
+                "reward": 0.0,
+                "creation_time": 1727388678.5980184,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-5000032.pt"
+                ]
+            }
+        ],
+        "elo": 1564.8693792877389,
+        "final_checkpoint": {
+            "steps": 5000032,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1727388678.5980184,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-5000032.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.4.1+cu121"
+    }
+}