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: RazPines/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:f164d6c574ae777d67095a2492910c913da52e3f136bdfb7896f0b16d67663c6
+size 1768747

SoccerTwos/SoccerTwos-1499486.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b26037b1daae04d16c3f4327c309ba37c4e02efb869919c1c33889b024e029c
+size 1768747

SoccerTwos/SoccerTwos-1499486.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65fa12bc44d68ccfef6e906e5f0a7b8e65b5e6a08a787442cf8500ccd4f21c4a
+size 28430358

SoccerTwos/SoccerTwos-1499532.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:359d8d661047f9ffc09df5f439b16827551ae89d283ca3e4fcbe96ec40c1c7ed
+size 14023820

SoccerTwos/SoccerTwos-1499532.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72cd7a5a8dd33392555bfe1df5e649dee304cf2ebe6127fb36a81014aca5556b
+size 151255030

SoccerTwos/SoccerTwos-19346.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79eaed33d2b7ff2a71595927c26b75f74655c73302d1adf04ea7a0b0c2988f75
+size 1766876

SoccerTwos/SoccerTwos-19346.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eab141a61156f9c31eb728f671e5a3da9011be5fc8c6df26cec48c863a91d756
+size 9479954

SoccerTwos/SoccerTwos-1942486.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94468db5def99357fa8d4ac5bfb3fe5686bb46d11bb289d8d100fe3a9feb2c3f
+size 1768747

SoccerTwos/SoccerTwos-1942486.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96f70d3368d8224f305c9c6b107edf86dc72290b149d1d16b605376bbd6bd144
+size 28430358

SoccerTwos/SoccerTwos-1942497.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94468db5def99357fa8d4ac5bfb3fe5686bb46d11bb289d8d100fe3a9feb2c3f
+size 1768747

SoccerTwos/SoccerTwos-1942497.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4437ad2f5aff9483f03b61b42f39fabbcef87ddbad5e4d9154c8733a8f7a9815
+size 28431638

SoccerTwos/SoccerTwos-1999614.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e23fdd6873fe1af6076a64ce9cc1c21e162e81efd0750787816c529a02278fa0
+size 14023820

SoccerTwos/SoccerTwos-1999614.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7f1958149cd4f5f101eb93c625cb3f963f9b9b850f53eb9cfc22ec1966004c2
+size 151255030

SoccerTwos/SoccerTwos-1999996.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d409e375192c6622651a914cf77b0eb335dcfc068dd5ebc1ddda1b5a8c65230
+size 1768747

SoccerTwos/SoccerTwos-1999996.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c04dc7a36d80e58c20c07cafd872481a9567da035dc3e2be4654f886275d2d2a
+size 28431638

SoccerTwos/SoccerTwos-2079076.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eea7fcad046b2baa6f998de332ef98eab5f37c839da39a38b741a756731ff40b
+size 14023820

SoccerTwos/SoccerTwos-2079076.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7fd9f7b6f7e8d9e0c35cb194dd7667a7ae3cfede00633c0ec477bfff00ae222
+size 151255030

SoccerTwos/SoccerTwos-2134665.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:371b3ba373460d47a68ce62f32c2ed0a11566c6774b8a7091cbbe2158c6a23a1
+size 1768747

SoccerTwos/SoccerTwos-2134665.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f73b99c8b18a8b893f12adb4a82c784d71e262711382dc26ef50e5e06b545ab
+size 28431638

SoccerTwos/SoccerTwos-22206.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bde7479a2859a9fe139f68f51801fc655590e163fcec200e6b43d329f5623c48
+size 1768747

SoccerTwos/SoccerTwos-22206.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b9221aaa4cad9f08d95e056b58c16abcc19f8eb8146c8882ab1baf26fc0c3a7
+size 28431774

SoccerTwos/SoccerTwos-36684.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f164d6c574ae777d67095a2492910c913da52e3f136bdfb7896f0b16d67663c6
+size 1768747

SoccerTwos/SoccerTwos-36684.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a515620ba2bbc574c05be19387dbcc74e5ec8c6afdfa68fba1cd38fb231635d0
+size 28431774

SoccerTwos/SoccerTwos-499937.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bda0061efe3b9c7b217ce96f6cbe8703fdc55142bd0c820cc624a4a7a29e3cbd
+size 14023820

SoccerTwos/SoccerTwos-499937.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d904bdd30c60e51898d4cb48866ced7e0613557da39f45b579b1f50be4df8e4
+size 151254874

SoccerTwos/SoccerTwos-999034.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:511af2446dc00b24e231b8afe3a4118aef8e33d223716fbe38066c7a866f3757
+size 14023820

SoccerTwos/SoccerTwos-999034.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88507bdce6eda195c75b2853cbd8ac0d5a74ca01c2055ab18498beca7a9aecc1
+size 151254874

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:843dab8054ef24592d4327aec778c4bc435088c660a64f3c52ceb2fb32461971
+size 28431030

SoccerTwos/events.out.tfevents.1717276642.BlackPC.27256.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1322e285cdc9145415f32ec7267ee3cb0c4ee6c158d5d1b0808478f91ed91eba
+size 27158

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 16384, "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/SoccerTwos.exe", "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": true, "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: 16384
+      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/SoccerTwos.exe
+  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: true
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: cuda
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,334 @@
+Mono path[0] = 'C:/projects/RL/huggingFaceCourse/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = 'C:/projects/RL/huggingFaceCourse/ml-agents/training-envs-executables/SoccerTwos/MonoBleedingEdge/etc'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path C:/projects/RL/huggingFaceCourse/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  0.064 seconds
+ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Microsoft Media Foundation video decoding to texture disabled: graphics device is Null, only Direct3D 11 and Direct3D 12 (only on desktop) are supported for hardware-accelerated video decoding.
+ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: '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: 0.832000 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+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 8 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]: 797 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.0 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 366 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 68.0 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 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 54 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 54 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 54 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 14]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 54 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_Job.Worker 13]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 8
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 54 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 54 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 54 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 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 15
+      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 54 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_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 8]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 10]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 11]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 488 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 12]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 54 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 0.9 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 798 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 5.1 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 798 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.3 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 0.9 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 797 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]: 798 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 173.6 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 2
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.9 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 798 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]: 797 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 3.2 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 0.9 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 798 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]: 797 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 +1,361 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 3.294991970062256,
+            "min": 3.294991970062256,
+            "max": 3.295747995376587,
+            "count": 3
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 59889.7734375,
+            "min": 59889.7734375,
+            "max": 105463.9375,
+            "count": 3
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 619.5,
+            "min": 492.5,
+            "max": 885.75,
+            "count": 3
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19824.0,
+            "min": 11820.0,
+            "max": 28344.0,
+            "count": 3
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1200.2216125847149,
+            "min": 1198.512895997199,
+            "max": 1200.2216125847149,
+            "count": 3
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 12002.21612584715,
+            "min": 4795.014370276737,
+            "max": 12002.21612584715,
+            "count": 3
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 29579.0,
+            "min": 9188.0,
+            "max": 29579.0,
+            "count": 3
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 29579.0,
+            "min": 9188.0,
+            "max": 29579.0,
+            "count": 3
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": 0.04330986738204956,
+            "min": 0.04330986738204956,
+            "max": 0.04582947865128517,
+            "count": 3
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": 0.692957878112793,
+            "min": 0.5041242837905884,
+            "max": 0.7332154512405396,
+            "count": 3
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.05042207986116409,
+            "min": 0.04577548801898956,
+            "max": 0.05042207986116409,
+            "count": 3
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 0.8067532777786255,
+            "min": 0.5035683512687683,
+            "max": 0.8067532777786255,
+            "count": 3
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 3
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 3
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.08561250194907188,
+            "min": -0.36363636363636365,
+            "max": 0.11101250350475311,
+            "count": 3
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 1.3698000311851501,
+            "min": -4.0,
+            "max": 1.7762000560760498,
+            "count": 3
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.08561250194907188,
+            "min": -0.36363636363636365,
+            "max": 0.11101250350475311,
+            "count": 3
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 1.3698000311851501,
+            "min": -4.0,
+            "max": 1.7762000560760498,
+            "count": 3
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 3
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 3
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.0021249399287626147,
+            "min": 0.0021249399287626147,
+            "max": 0.0021249399287626147,
+            "count": 1
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.0021249399287626147,
+            "min": 0.0021249399287626147,
+            "max": 0.0021249399287626147,
+            "count": 1
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.007496952001626293,
+            "min": 0.007496952001626293,
+            "max": 0.007496952001626293,
+            "count": 1
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.007496952001626293,
+            "min": 0.007496952001626293,
+            "max": 0.007496952001626293,
+            "count": 1
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.004695787249753873,
+            "min": 0.004695787249753873,
+            "max": 0.004695787249753873,
+            "count": 1
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.004695787249753873,
+            "min": 0.004695787249753873,
+            "max": 0.004695787249753873,
+            "count": 1
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 1
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 1
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000004,
+            "min": 0.20000000000000004,
+            "max": 0.20000000000000004,
+            "count": 1
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000004,
+            "min": 0.20000000000000004,
+            "max": 0.20000000000000004,
+            "count": 1
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005,
+            "min": 0.005,
+            "max": 0.005,
+            "count": 1
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005,
+            "min": 0.005,
+            "max": 0.005,
+            "count": 1
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1717276638",
+        "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul  5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]",
+        "command_line_arguments": "\\\\?\\C:\\Users\\Jeste\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --torch-device cuda --force",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.3.0",
+        "numpy_version": "1.24.3",
+        "end_time_seconds": "1717276694"
+    },
+    "total": 55.94161929999973,
+    "count": 1,
+    "self": 0.005248999994364567,
+    "children": {
+        "run_training.setup": {
+            "total": 0.07311640000261832,
+            "count": 1,
+            "self": 0.07311640000261832
+        },
+        "TrainerController.start_learning": {
+            "total": 55.863253900002746,
+            "count": 1,
+            "self": 0.042421900034241844,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 4.344175300000643,
+                    "count": 1,
+                    "self": 4.344175300000643
+                },
+                "TrainerController.advance": {
+                    "total": 51.28443339997466,
+                    "count": 2670,
+                    "self": 0.037352400344389025,
+                    "children": {
+                        "env_step": {
+                            "total": 43.60035759991297,
+                            "count": 2670,
+                            "self": 23.51200740026252,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 20.063391899806447,
+                                    "count": 2670,
+                                    "self": 0.22031719956430607,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 19.84307470024214,
+                                            "count": 5318,
+                                            "self": 19.84307470024214
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.024958299844001886,
+                                    "count": 2669,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 52.217857700066816,
+                                            "count": 2669,
+                                            "is_parallel": true,
+                                            "self": 33.69345090002753,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.0015405000012833625,
+                                                    "count": 2,
+                                                    "is_parallel": true,
+                                                    "self": 0.00031939999462338164,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.0012211000066599809,
+                                                            "count": 8,
+                                                            "is_parallel": true,
+                                                            "self": 0.0012211000066599809
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 18.522866300038004,
+                                                    "count": 2669,
+                                                    "is_parallel": true,
+                                                    "self": 1.0449094994692132,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 0.8874818002150278,
+                                                            "count": 2669,
+                                                            "is_parallel": true,
+                                                            "self": 0.8874818002150278
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 13.233655100215401,
+                                                            "count": 2669,
+                                                            "is_parallel": true,
+                                                            "self": 13.233655100215401
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 3.356819900138362,
+                                                            "count": 5338,
+                                                            "is_parallel": true,
+                                                            "self": 0.6450732003140729,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 2.711746699824289,
+                                                                    "count": 21352,
+                                                                    "is_parallel": true,
+                                                                    "self": 2.711746699824289
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 7.6467233997173025,
+                            "count": 2669,
+                            "self": 0.2873427996528335,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 3.6102151000668528,
+                                    "count": 2669,
+                                    "self": 3.6102151000668528
+                                },
+                                "_update_policy": {
+                                    "total": 3.7491654999976163,
+                                    "count": 1,
+                                    "self": 2.3679731999945943,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 1.381192300003022,
+                                            "count": 3,
+                                            "self": 1.381192300003022
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 9.999930625781417e-07,
+                    "count": 1,
+                    "self": 9.999930625781417e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.1922223000001395,
+                    "count": 1,
+                    "self": 0.0077162000015960075,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.1845060999985435,
+                            "count": 1,
+                            "self": 0.1845060999985435
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,30 @@
+{
+    "SoccerTwos": {
+        "elo": 1199.0236832717028,
+        "checkpoints": [
+            {
+                "steps": 36684,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-36684.onnx",
+                "reward": 0.0,
+                "creation_time": 1717276694.5476358,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-36684.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 36684,
+            "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1717276694.5476358,
+            "auxillary_file_paths": [
+                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-36684.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.3.0"
+    }
+}