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: Wembo/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 sha256:9d59f2f8745b2653f9297f4db4c1cad14261869dfd76b87d1f6c40376be259aa
+size 1768747

SoccerTwos/SoccerTwos-48499962.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f731eafe226d938b581648ad90560a91c0474c3ca6a5caf0b9993ea75e91afc
+size 1768747

SoccerTwos/SoccerTwos-48499962.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8708d8c30dff7a65f692203e1951033000895bd30cf1501cd41596cfa973e77f
+size 28430482

SoccerTwos/SoccerTwos-48999994.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16b9314faa3f8ef02e728e7aff50c3684ee91a82bbd35daa08615c8d24655d7e
+size 1768747

SoccerTwos/SoccerTwos-48999994.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e451c8e5bf378076c84ffaeba5bb0660772e586e21ff87fc22e5946765536af3
+size 28430482

SoccerTwos/SoccerTwos-49499993.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:281af5ae6d43d97ae724e63b912ffbd4aef44156f26e171fb69245012fab18d5
+size 1768747

SoccerTwos/SoccerTwos-49499993.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8793c10a7b87d4b71c06a24a5f73576d35c89dcec5893927b599619e93553ab5
+size 28430482

SoccerTwos/SoccerTwos-49999896.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d59f2f8745b2653f9297f4db4c1cad14261869dfd76b87d1f6c40376be259aa
+size 1768747

SoccerTwos/SoccerTwos-49999896.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c025f2c5c020ecf5257ce92c5a7ad081002a7a5aa8a679892e2646542251082a
+size 28430482

SoccerTwos/SoccerTwos-50000034.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d59f2f8745b2653f9297f4db4c1cad14261869dfd76b87d1f6c40376be259aa
+size 1768747

SoccerTwos/SoccerTwos-50000034.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1d2b3251717a5bd7ca2b719bb758e28b300a34be19746713bad7a7996f7a0f5
+size 28430482

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8640d36723d31b6c353d04e895d5e32e195416934efaecbf5103c4f0ba766628
+size 28429366

SoccerTwos/events.out.tfevents.1757986168.JQ7Q3VTQPP.49137.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a56e663ded920175db76a22fbee8bfbd8400d5892bed9c4d98b15cd3807d32a6
+size 1241

SoccerTwos/events.out.tfevents.1757986218.JQ7Q3VTQPP.50158.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d467fe512f0a266ceb4300110d67a86666679362f5ba5f06f276640ffda69b1
+size 13375143

SoccerTwos/events.out.tfevents.1758097570.JQ7Q3VTQPP.50070.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a3fc238ac6e1d5d4c7ccaba758c0e411d1d28ba0392367a0bdabd146eddff55
+size 5489249

SoccerTwos/events.out.tfevents.1758160981.JQ7Q3VTQPP.21989.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:593788cfa35efa152a5e0318c3aa27e752fe62b7d2b26109bed704c750ae5a3d
+size 10577085

SoccerTwos/events.out.tfevents.1758245419.JQ7Q3VTQPP.9811.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d58754b60a40b119596daacc04cb860a5805f5aebb22f9641bf405c51022c002
+size 11748655

SoccerTwos/events.out.tfevents.1758324360.JQ7Q3VTQPP.10444.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9399984418bf92e9f877d761459e65be4be2c3eb4f580fbecff82dc5748bd04
+size 3916815

SoccerTwos/events.out.tfevents.1758375755.JQ7Q3VTQPP.6621.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5cf67e52a6f12876640a7d258fcf1db5ada4428b45b27fd71cd0b83cea45cd0
+size 5438007

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 50000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos/SoccerTwos.app", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,84 @@
+default_settings: null
+behaviors:
+  SoccerTwos:
+    trainer_type: poca
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: constant
+      beta_schedule: constant
+      epsilon_schedule: constant
+    checkpoint_interval: 500000
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 2
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+    init_path: null
+    keep_checkpoints: 5
+    even_checkpoints: false
+    max_steps: 50000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 50000
+      team_change: 200000
+      swap_steps: 2000
+      window: 10
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/SoccerTwos/SoccerTwos.app
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  timeout_wait: 60
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: SoccerTwos
+  initialize_from: null
+  load_model: false
+  resume: true
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,318 @@
+Mono path[0] = '/Users/bytedance/Desktop/Code/ml-agents-develop/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/Resources/Data/Managed'
+Mono config path = '/Users/bytedance/Desktop/Code/ml-agents-develop/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/MonoBleedingEdge/etc'
+New input system (experimental) initialized
+Initialize engine version: 2021.3.17f1 (3e8111cac19d)
+[Subsystems] Discovering subsystems at path /Users/bytedance/Desktop/Code/ml-agents-develop/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/Resources/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  0.058 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: 0.261834 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Thread 0x16f33f000 may have been prematurely finalized
+Setting up 7 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]: 99518 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 150 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 78.8 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.7 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 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 7
+      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 13
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 9]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 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 8]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_OSX HID Input]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 10]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 11]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 12]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_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 6
+    [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]: 99519 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 5.0 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 99519 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]: 99518 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]: 99519 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]: 99519 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]: 99518 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 3.4 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]: 99519 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]: 99518 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 +1,368 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 1.338965654373169,
+            "min": 1.324674129486084,
+            "max": 1.4820914268493652,
+            "count": 529
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 28750.26953125,
+            "min": 12932.3828125,
+            "max": 34238.1328125,
+            "count": 529
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 63.62337662337662,
+            "min": 48.9,
+            "max": 104.39583333333333,
+            "count": 529
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19596.0,
+            "min": 8320.0,
+            "max": 21144.0,
+            "count": 529
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1577.023942818566,
+            "min": 1516.960081543736,
+            "max": 1596.9525960602211,
+            "count": 529
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 242861.68719405917,
+            "min": 129215.92325248342,
+            "max": 314710.23985551286,
+            "count": 529
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 49999896.0,
+            "min": 44719978.0,
+            "max": 49999896.0,
+            "count": 529
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 49999896.0,
+            "min": 44719978.0,
+            "max": 49999896.0,
+            "count": 529
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": 0.0183502659201622,
+            "min": -0.10091569274663925,
+            "max": 0.08867570012807846,
+            "count": 529
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": 2.8442912101745605,
+            "min": -16.00824737548828,
+            "max": 13.478706359863281,
+            "count": 529
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.016256773844361305,
+            "min": -0.10263310372829437,
+            "max": 0.08865656703710556,
+            "count": 529
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2.5197999477386475,
+            "min": -16.21603012084961,
+            "max": 13.475797653198242,
+            "count": 529
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 529
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 529
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.02403612905933011,
+            "min": -0.3715043486892313,
+            "max": 0.3895565785075489,
+            "count": 529
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -3.725600004196167,
+            "min": -51.26760011911392,
+            "max": 59.21259993314743,
+            "count": 529
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.02403612905933011,
+            "min": -0.3715043486892313,
+            "max": 0.3895565785075489,
+            "count": 529
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -3.725600004196167,
+            "min": -51.26760011911392,
+            "max": 59.21259993314743,
+            "count": 529
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 529
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 529
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.01577699922490865,
+            "min": 0.013006098271580413,
+            "max": 0.024623570271069185,
+            "count": 256
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.01577699922490865,
+            "min": 0.013006098271580413,
+            "max": 0.024623570271069185,
+            "count": 256
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.08750425999363264,
+            "min": 0.07417696664730708,
+            "max": 0.11233750507235526,
+            "count": 256
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.08750425999363264,
+            "min": 0.07417696664730708,
+            "max": 0.11233750507235526,
+            "count": 256
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.0891955646375815,
+            "min": 0.07468820090095202,
+            "max": 0.1133206898967425,
+            "count": 256
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.0891955646375815,
+            "min": 0.07468820090095202,
+            "max": 0.1133206898967425,
+            "count": 256
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 256
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 256
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 256
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 256
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 256
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 256
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1758375752",
+        "python_version": "3.10.9 | packaged by conda-forge | (main, Feb  2 2023, 20:26:08) [Clang 14.0.6 ]",
+        "command_line_arguments": "/Users/bytedance/miniconda3/envs/py310/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --resume --no-graphics",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.2.1",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1758390059"
+    },
+    "total": 14307.048529458989,
+    "count": 1,
+    "self": 0.18879537598695606,
+    "children": {
+        "run_training.setup": {
+            "total": 0.02637237499584444,
+            "count": 1,
+            "self": 0.02637237499584444
+        },
+        "TrainerController.start_learning": {
+            "total": 14306.833361708006,
+            "count": 1,
+            "self": 3.1894730314670596,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 4.4594791699782945,
+                    "count": 28,
+                    "self": 4.4594791699782945
+                },
+                "TrainerController.advance": {
+                    "total": 14299.07872359056,
+                    "count": 363140,
+                    "self": 2.8804629847290926,
+                    "children": {
+                        "env_step": {
+                            "total": 11628.534124710743,
+                            "count": 363140,
+                            "self": 11256.114741745841,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 370.5493276050838,
+                                    "count": 363140,
+                                    "self": 12.03670942413737,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 358.51261818094645,
+                                            "count": 663468,
+                                            "self": 358.51261818094645
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 1.8700553598173428,
+                                    "count": 363140,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 14298.299049386347,
+                                            "count": 363140,
+                                            "is_parallel": true,
+                                            "self": 3474.274603054626,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.03197337602614425,
+                                                    "count": 56,
+                                                    "is_parallel": true,
+                                                    "self": 0.003829363820841536,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.028144012205302715,
+                                                            "count": 224,
+                                                            "is_parallel": true,
+                                                            "self": 0.028144012205302715
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 10823.992472955695,
+                                                    "count": 363140,
+                                                    "is_parallel": true,
+                                                    "self": 28.315567062818445,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 214.86046016105684,
+                                                            "count": 363140,
+                                                            "is_parallel": true,
+                                                            "self": 214.86046016105684
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 10204.06977807256,
+                                                            "count": 363140,
+                                                            "is_parallel": true,
+                                                            "self": 10204.06977807256
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 376.7466676592594,
+                                                            "count": 726280,
+                                                            "is_parallel": true,
+                                                            "self": 44.09290096539189,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 332.6537666938675,
+                                                                    "count": 2905120,
+                                                                    "is_parallel": true,
+                                                                    "self": 332.6537666938675
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 2667.6641358950874,
+                            "count": 363140,
+                            "self": 23.78160260844743,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 576.4138045783911,
+                                    "count": 363140,
+                                    "self": 574.8806223684514,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 1.533182209939696,
+                                            "count": 11,
+                                            "self": 1.533182209939696
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 2067.468728708249,
+                                    "count": 256,
+                                    "self": 247.78706047486048,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 1819.6816682333883,
+                                            "count": 7680,
+                                            "self": 1819.6816682333883
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 4.580069798976183e-07,
+                    "count": 1,
+                    "self": 4.580069798976183e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.10568545799469575,
+                    "count": 1,
+                    "self": 0.0006127909873612225,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.10507266700733453,
+                            "count": 1,
+                            "self": 0.10507266700733453
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.2.1"
+    },
+    "SoccerTwos": {
+        "elo": 1575.4705225488835,
+        "checkpoints": [
+            {
+                "steps": 48499962,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-48499962.onnx",
+                "reward": 0.0,
+                "creation_time": 1758386025.1252348,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-48499962.pt"
+                ]
+            },
+            {
+                "steps": 48999994,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-48999994.onnx",
+                "reward": 0.0,
+                "creation_time": 1758387367.433439,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-48999994.pt"
+                ]
+            },
+            {
+                "steps": 49499993,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-49499993.onnx",
+                "reward": 0.0,
+                "creation_time": 1758388712.371624,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-49499993.pt"
+                ]
+            },
+            {
+                "steps": 49999896,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-49999896.onnx",
+                "reward": 0.0,
+                "creation_time": 1758390059.351677,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-49999896.pt"
+                ]
+            },
+            {
+                "steps": 50000034,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-50000034.onnx",
+                "reward": 0.0,
+                "creation_time": 1758390059.468441,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-50000034.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 50000034,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1758390059.468441,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-50000034.pt"
+            ]
+        }
+    }
+}