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: spenning/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 sha256:7a54f2ad4298568cea68af76b3f30b224df5f8755ee20ae0834f3f23e12c10ae
+size 1768747

SoccerTwos/SoccerTwos-3499864.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b908c5051fe209b4a8d4c3be1be80814ff8c77736b3d855dc329246caeb4935b
+size 1768747

SoccerTwos/SoccerTwos-3499864.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84389db74dc66481518980a78f3e9773a0d77f94196376714cf4a243c50f62d4
+size 28430358

SoccerTwos/SoccerTwos-3999926.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6768b55c6c04d8cec9b23569798a64bd9a43113334b1e2b34de70c7fe8f84968
+size 1768747

SoccerTwos/SoccerTwos-3999926.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a62edae54cf2c9578932fe7535831bbc026e9532dc5504346d500142ad599703
+size 28430358

SoccerTwos/SoccerTwos-4499964.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:add7bc4c716cb12b2208cfd2ef700721da4e71c2a727959feaae1b3aa9205c17
+size 1768747

SoccerTwos/SoccerTwos-4499964.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18e865602cd02b2c9f4713e8a726c6d3af59ae1133a40a7298bc9d57deb406f4
+size 28430358

SoccerTwos/SoccerTwos-4999936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6e9770791b1ab6e74a335d30136e05ce7a7a5c2179dc9ebcb1f0be6278c7890
+size 1768747

SoccerTwos/SoccerTwos-4999936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01ac3814df50cb4804e211e9d7ae4ccfe80b3441cc73a6b1aec84195d417abc6
+size 28430358

SoccerTwos/SoccerTwos-5224692.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a54f2ad4298568cea68af76b3f30b224df5f8755ee20ae0834f3f23e12c10ae
+size 1768747

SoccerTwos/SoccerTwos-5224692.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:243db3688a9249741b28d731bd19eb76702d2cd73773bfe725f47dfc351a57cb
+size 28430358

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fc5b67bae00168c81a14134cab911c8bd5c577f2b1a3081f33b9484355f2491
+size 28429366

SoccerTwos/events.out.tfevents.1735936391.rl3.1352.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c336f21f7d8736649a5adb08d1b325711b48c2e9a4e0ced3bd900d0b89c5aaeb
+size 5275418

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 50000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/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": "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: 50000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 50000
+      team_change: 200000
+      swap_steps: 2000
+      window: 10
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/linux/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: 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 +1,509 @@
+Mono path[0] = '/home/ubuntu/unit_5/ml-agents/training-envs-executables/linux/SoccerTwos_Data/Managed'
+Mono config path = '/home/ubuntu/unit_5/ml-agents/training-envs-executables/linux/SoccerTwos_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+PlayerPrefs - Creating folder: /home/ubuntu/.config/unity3d/Unity Technologies/SoccerTwos
+Unable to load player prefs
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /home/ubuntu/unit_5/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  0.068 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: 0.468950 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
+Setting up 1 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]: 98678 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]
+      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]
+      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_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_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]: 98679 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]: 98679 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]: 98678 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]: 98679 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]: 98679 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]: 98678 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]: 98679 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]: 98678 frames, [2.0 KB-4.0 KB]: 1 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 2.2 KB
+      Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -0,0 +1,424 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 1.746320128440857,
+            "min": 1.7363805770874023,
+            "max": 3.2957584857940674,
+            "count": 522
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 34255.81640625,
+            "min": 1157.860107421875,
+            "max": 111787.09375,
+            "count": 522
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 56.72093023255814,
+            "min": 43.690265486725664,
+            "max": 999.0,
+            "count": 522
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19512.0,
+            "min": 860.0,
+            "max": 30456.0,
+            "count": 522
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1613.6541639199497,
+            "min": 1196.3821187916237,
+            "max": 1646.058246862515,
+            "count": 520
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 277548.51619423134,
+            "min": 2392.7642375832474,
+            "max": 353599.2608974506,
+            "count": 520
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 5219836.0,
+            "min": 9246.0,
+            "max": 5219836.0,
+            "count": 522
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 5219836.0,
+            "min": 9246.0,
+            "max": 5219836.0,
+            "count": 522
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.021065326407551765,
+            "min": -0.114939846098423,
+            "max": 0.23402521014213562,
+            "count": 522
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -3.644301414489746,
+            "min": -19.884593963623047,
+            "max": 34.6357307434082,
+            "count": 522
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.02172704227268696,
+            "min": -0.10988207906484604,
+            "max": 0.23309262096881866,
+            "count": 522
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -3.7587783336639404,
+            "min": -19.009599685668945,
+            "max": 34.49770736694336,
+            "count": 522
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 522
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 522
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.09753526152902944,
+            "min": -0.6503200004498164,
+            "max": 0.5138222166785488,
+            "count": 522
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -16.873600244522095,
+            "min": -60.31759977340698,
+            "max": 67.16399997472763,
+            "count": 522
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.09753526152902944,
+            "min": -0.6503200004498164,
+            "max": 0.5138222166785488,
+            "count": 522
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -16.873600244522095,
+            "min": -60.31759977340698,
+            "max": 67.16399997472763,
+            "count": 522
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 522
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 522
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.017220419994555414,
+            "min": 0.010488389624515548,
+            "max": 0.02401322474082311,
+            "count": 251
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.017220419994555414,
+            "min": 0.010488389624515548,
+            "max": 0.02401322474082311,
+            "count": 251
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.10476486931244532,
+            "min": 0.000891920831054449,
+            "max": 0.11985189691185952,
+            "count": 251
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.10476486931244532,
+            "min": 0.000891920831054449,
+            "max": 0.11985189691185952,
+            "count": 251
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.10669645244876544,
+            "min": 0.0009079295831422011,
+            "max": 0.12237524365385373,
+            "count": 251
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.10669645244876544,
+            "min": 0.0009079295831422011,
+            "max": 0.12237524365385373,
+            "count": 251
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 251
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 251
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.19999999999999996,
+            "max": 0.20000000000000007,
+            "count": 251
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.19999999999999996,
+            "max": 0.20000000000000007,
+            "count": 251
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005,
+            "max": 0.005000000000000001,
+            "count": 251
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005,
+            "max": 0.005000000000000001,
+            "count": 251
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1735936390",
+        "python_version": "3.10.12 (main, Nov  6 2024, 20:22:13) [GCC 11.4.0]",
+        "command_line_arguments": "/home/ubuntu/unit_5/.env/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos --run-id=SoccerTwos --no-graphics",
+        "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": "1735953422"
+    },
+    "total": 17031.740450696,
+    "count": 1,
+    "self": 0.01577904200166813,
+    "children": {
+        "run_training.setup": {
+            "total": 0.019938700000011522,
+            "count": 1,
+            "self": 0.019938700000011522
+        },
+        "TrainerController.start_learning": {
+            "total": 17031.704732954,
+            "count": 1,
+            "self": 8.163516731314303,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.438193596002179,
+                    "count": 27,
+                    "self": 2.438193596002179
+                },
+                "TrainerController.advance": {
+                    "total": 17020.679267017687,
+                    "count": 358200,
+                    "self": 8.045691637758864,
+                    "children": {
+                        "env_step": {
+                            "total": 5821.830811329741,
+                            "count": 358200,
+                            "self": 4451.505804111353,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 1365.642184401362,
+                                    "count": 358200,
+                                    "self": 43.187180902876435,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 1322.4550034984857,
+                                            "count": 657866,
+                                            "self": 1322.4550034984857
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 4.682822817025794,
+                                    "count": 358200,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 16993.021770557774,
+                                            "count": 358200,
+                                            "is_parallel": true,
+                                            "self": 13393.358438073206,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.011267751999980646,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.009102380000285848,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0021653719996947984,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0021653719996947984
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.03513316900000518,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0004681939999500173,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00041234900004383235,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00041234900004383235
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.03279391300009138,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.03279391300009138
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0014587129999199533,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003181890000405474,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.001140523999879406,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.001140523999879406
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 3599.6218233665686,
+                                                    "count": 358199,
+                                                    "is_parallel": true,
+                                                    "self": 162.3637285902014,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 125.94311413460105,
+                                                            "count": 358199,
+                                                            "is_parallel": true,
+                                                            "self": 125.94311413460105
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 2810.2099029702003,
+                                                            "count": 358199,
+                                                            "is_parallel": true,
+                                                            "self": 2810.2099029702003
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 501.10507767156537,
+                                                            "count": 716398,
+                                                            "is_parallel": true,
+                                                            "self": 108.99582342730048,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 392.1092542442649,
+                                                                    "count": 2865592,
+                                                                    "is_parallel": true,
+                                                                    "self": 392.1092542442649
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.041509117998884903,
+                                                    "count": 52,
+                                                    "is_parallel": true,
+                                                    "self": 0.0090236569812987,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.032485461017586204,
+                                                            "count": 208,
+                                                            "is_parallel": true,
+                                                            "self": 0.032485461017586204
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 11190.80276405019,
+                            "count": 358200,
+                            "self": 55.73654757817167,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 1692.7785150610093,
+                                    "count": 358200,
+                                    "self": 1691.568150410012,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 1.210364650997235,
+                                            "count": 10,
+                                            "self": 1.210364650997235
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 9442.287701411009,
+                                    "count": 252,
+                                    "self": 611.3340144709218,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 8830.953686940087,
+                                            "count": 7547,
+                                            "self": 8830.953686940087
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 4.07900006393902e-06,
+                    "count": 1,
+                    "self": 4.07900006393902e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.4237515299973893,
+                    "count": 1,
+                    "self": 0.007506959998863749,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.41624456999852555,
+                            "count": 1,
+                            "self": 0.41624456999852555
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 3499864,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3499864.onnx",
+                "reward": 0.0,
+                "creation_time": 1735947653.8642848,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-3499864.pt"
+                ]
+            },
+            {
+                "steps": 3999926,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3999926.onnx",
+                "reward": 0.0,
+                "creation_time": 1735949272.8096864,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-3999926.pt"
+                ]
+            },
+            {
+                "steps": 4499964,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-4499964.onnx",
+                "reward": 0.0,
+                "creation_time": 1735950915.4964442,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-4499964.pt"
+                ]
+            },
+            {
+                "steps": 4999936,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-4999936.onnx",
+                "reward": 0.0,
+                "creation_time": 1735952610.171939,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-4999936.pt"
+                ]
+            },
+            {
+                "steps": 5224692,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-5224692.onnx",
+                "reward": null,
+                "creation_time": 1735953422.398052,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-5224692.pt"
+                ]
+            }
+        ],
+        "elo": 1603.65757012147,
+        "final_checkpoint": {
+            "steps": 5224692,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": null,
+            "creation_time": 1735953422.398052,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-5224692.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.5.1+cu124"
+    }
+}