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: Snorlax/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 sha256:62f600f37d4fe504140ff0b7d461b0b2c18ce9e64bfa5f68222e9423d655bb11
+size 1768747

SoccerTwos/SoccerTwos-48499904.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48e43c46a07c86d18b36f466c87dbdaa6b9761c20d06c811706add51b0021fa8
+size 1768747

SoccerTwos/SoccerTwos-48499904.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c14740558b3109f6b5cacfb5bb3b677e29bdb5717a3f263fdfafbd6fdd1b7fd
+size 28432146

SoccerTwos/SoccerTwos-48999950.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0851f7f4b59707dceafc5185033d40982524ff816bd38a0e8006fd3bb8ff2f32
+size 1768747

SoccerTwos/SoccerTwos-48999950.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f69dbfce05247401a32e6932e4ed2284e9fc3b324cb4f7ed195a28a37cb8686e
+size 28432146

SoccerTwos/SoccerTwos-49499806.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dd16b73d1d1c596381384b9883653aa502441b916a86ff215b8061688862628
+size 1768747

SoccerTwos/SoccerTwos-49499806.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30d8a701f684b2cd947d4e1e03b43717404cff802518180cc3348d257cbe086c
+size 28432146

SoccerTwos/SoccerTwos-49999984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62f600f37d4fe504140ff0b7d461b0b2c18ce9e64bfa5f68222e9423d655bb11
+size 1768747

SoccerTwos/SoccerTwos-49999984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48a8b81bc09dfa22cae8d36176982c3fbfdc110b4b3f9f70e46b5e4953e70a66
+size 28432146

SoccerTwos/SoccerTwos-50000036.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62f600f37d4fe504140ff0b7d461b0b2c18ce9e64bfa5f68222e9423d655bb11
+size 1768747

SoccerTwos/SoccerTwos-50000036.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68e29eec25c9a64897ccce7ebe57e116ccf3e65c0fffa4bd11ae82e6f7fbf344
+size 28432146

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fc324b2a3acfecc6607fd69ee45b149c92c0724aa338d7bf2c63e03205d03d9
+size 28431030

SoccerTwos/events.out.tfevents.1733661845.LAPTOP-8ALNSR00.80865.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:409825ae590e16d6381a00090a5f61f3555dd782b84d32f7dab327980fda6340
+size 32333154

SoccerTwos/events.out.tfevents.1733752631.LAPTOP-8ALNSR00.1184.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5feeb031a836f2d5b5ac834f910f16d766cd7d37db3b7e586e5041f9cb62d13e
+size 18953407

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": 100000, "team_change": 500000, "swap_steps": 10000, "window": 30, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "../ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos-debug", "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: 100000
+      team_change: 500000
+      swap_steps: 10000
+      window: 30
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: ../ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.x86_64
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  timeout_wait: 60
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: SoccerTwos-debug
+  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 +1,404 @@
+Mono path[0] = '/home/zhangsz/Workspace/HF_Deep_RL_Course/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = '/home/zhangsz/Workspace/HF_Deep_RL_Course/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /home/zhangsz/Workspace/HF_Deep_RL_Course/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  0.065 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: 0.392842 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
+Setting up 16 worker threads for Enlighten.
+Memory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [8.0 KB-16.0 KB]: 346270 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.1 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 18]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 300.0 KB
+      Peak Allocated Bytes 249.6 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 16]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 27]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 14]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.7 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 17]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 31
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 20]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 11]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 30]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 21]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 26]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 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 25]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 29]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 13]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 16
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 28]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 22]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 9]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 8]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 23]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 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_Job.Worker 24]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 15]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 12]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 19]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 131 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]: 346271 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]: 346271 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]: 346270 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]: 346271 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]: 346271 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]: 346270 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]: 346271 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]: 346270 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": 1.382171869277954,
+            "min": 1.3406294584274292,
+            "max": 1.5941110849380493,
+            "count": 1844
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 24901.208984375,
+            "min": 21594.4140625,
+            "max": 36567.2734375,
+            "count": 1844
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 72.20588235294117,
+            "min": 44.31818181818182,
+            "max": 104.61702127659575,
+            "count": 1844
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19640.0,
+            "min": 14520.0,
+            "max": 21788.0,
+            "count": 1844
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1880.319441975431,
+            "min": 1797.6161456333896,
+            "max": 1892.5716559389089,
+            "count": 1844
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 255723.4441086586,
+            "min": 175502.58311787687,
+            "max": 410920.08707172686,
+            "count": 1844
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 49999984.0,
+            "min": 31569976.0,
+            "max": 49999984.0,
+            "count": 1844
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 49999984.0,
+            "min": 31569976.0,
+            "max": 49999984.0,
+            "count": 1844
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.008061565458774567,
+            "min": -0.13645006716251373,
+            "max": 0.1033400148153305,
+            "count": 1844
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -1.0963728427886963,
+            "min": -24.922229766845703,
+            "max": 16.017702102661133,
+            "count": 1844
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.008827511221170425,
+            "min": -0.13706254959106445,
+            "max": 0.10023332387208939,
+            "count": 1844
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -1.2005414962768555,
+            "min": -25.208498001098633,
+            "max": 16.848989486694336,
+            "count": 1844
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 1844
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 1844
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.06327352979603935,
+            "min": -0.4349043472953465,
+            "max": 0.2952662448214877,
+            "count": 1844
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -8.605200052261353,
+            "min": -77.33240008354187,
+            "max": 62.98039984703064,
+            "count": 1844
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.06327352979603935,
+            "min": -0.4349043472953465,
+            "max": 0.2952662448214877,
+            "count": 1844
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -8.605200052261353,
+            "min": -77.33240008354187,
+            "max": 62.98039984703064,
+            "count": 1844
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 1844
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 1844
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.021826821127615404,
+            "min": 0.011657302830280969,
+            "max": 0.02609102944843471,
+            "count": 894
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.021826821127615404,
+            "min": 0.011657302830280969,
+            "max": 0.02609102944843471,
+            "count": 894
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.08605065693457921,
+            "min": 0.07169382013380528,
+            "max": 0.12169351130723953,
+            "count": 894
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.08605065693457921,
+            "min": 0.07169382013380528,
+            "max": 0.12169351130723953,
+            "count": 894
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.0873677298426628,
+            "min": 0.07212473005056382,
+            "max": 0.12342467854420344,
+            "count": 894
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.0873677298426628,
+            "min": 0.07212473005056382,
+            "max": 0.12342467854420344,
+            "count": 894
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 894
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 894
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 894
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 894
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 894
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 894
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1733752631",
+        "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
+        "command_line_arguments": "/home/zhangsz/anaconda3/envs/deep_rl_course/bin/mlagents-learn ./SoccerTwos.yaml --env=../ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos-debug --no-graphics --resume",
+        "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": "1733779195"
+    },
+    "total": 26564.170061824,
+    "count": 1,
+    "self": 5.735672844002693,
+    "children": {
+        "run_training.setup": {
+            "total": 0.016341089999997394,
+            "count": 1,
+            "self": 0.016341089999997394
+        },
+        "TrainerController.start_learning": {
+            "total": 26558.418047889998,
+            "count": 1,
+            "self": 16.27938580256523,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.4120728419996027,
+                    "count": 38,
+                    "self": 2.4120728419996027
+                },
+                "TrainerController.advance": {
+                    "total": 26539.586466513432,
+                    "count": 1267380,
+                    "self": 14.695409102725534,
+                    "children": {
+                        "env_step": {
+                            "total": 20610.8784505561,
+                            "count": 1267380,
+                            "self": 13519.42253980608,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 7080.059960516522,
+                                    "count": 1267380,
+                                    "self": 98.50023091266303,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 6981.559729603859,
+                                            "count": 2308482,
+                                            "self": 6981.559729603859
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 11.395950233499804,
+                                    "count": 1267380,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 26523.549686335948,
+                                            "count": 1267380,
+                                            "is_parallel": true,
+                                            "self": 14694.419936251274,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0017620039999926007,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.0007527659999979619,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0010092379999946388,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0010092379999946388
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.017917139000005022,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00029563500001472676,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0002221390000016754,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0002221390000016754
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.016483568999994702,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.016483568999994702
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.000915795999993918,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00022799099998849215,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0006878050000054259,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0006878050000054259
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.0303977620057978,
+                                                    "count": 74,
+                                                    "is_parallel": true,
+                                                    "self": 0.006590180996589368,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.023807581009208434,
+                                                            "count": 296,
+                                                            "is_parallel": true,
+                                                            "self": 0.023807581009208434
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 11829.099352322668,
+                                                    "count": 1267379,
+                                                    "is_parallel": true,
+                                                    "self": 328.7603502342481,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 203.86634577828423,
+                                                            "count": 1267379,
+                                                            "is_parallel": true,
+                                                            "self": 203.86634577828423
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 10340.955320573892,
+                                                            "count": 1267379,
+                                                            "is_parallel": true,
+                                                            "self": 10340.955320573892
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 955.517335736244,
+                                                            "count": 2534758,
+                                                            "is_parallel": true,
+                                                            "self": 207.19493583769452,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 748.3223998985495,
+                                                                    "count": 10139032,
+                                                                    "is_parallel": true,
+                                                                    "self": 748.3223998985495
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 5914.012606854603,
+                            "count": 1267380,
+                            "self": 122.59324357371406,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 3067.5393345179223,
+                                    "count": 1267380,
+                                    "self": 3062.31642538492,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 5.222909133002304,
+                                            "count": 37,
+                                            "self": 5.222909133002304
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 2723.8800287629674,
+                                    "count": 894,
+                                    "self": 1398.6412164982567,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 1325.2388122647108,
+                                            "count": 26820,
+                                            "self": 1325.2388122647108
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 4.6800050768069923e-07,
+                    "count": 1,
+                    "self": 4.6800050768069923e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.1401222640015476,
+                    "count": 1,
+                    "self": 0.0008723770006326959,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.1392498870009149,
+                            "count": 1,
+                            "self": 0.1392498870009149
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 48499904,
+                "file_path": "results/SoccerTwos-debug/SoccerTwos/SoccerTwos-48499904.onnx",
+                "reward": 0.0,
+                "creation_time": 1733777040.9802525,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos-debug/SoccerTwos/SoccerTwos-48499904.pt"
+                ]
+            },
+            {
+                "steps": 48999950,
+                "file_path": "results/SoccerTwos-debug/SoccerTwos/SoccerTwos-48999950.onnx",
+                "reward": 0.0,
+                "creation_time": 1733777759.0047858,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos-debug/SoccerTwos/SoccerTwos-48999950.pt"
+                ]
+            },
+            {
+                "steps": 49499806,
+                "file_path": "results/SoccerTwos-debug/SoccerTwos/SoccerTwos-49499806.onnx",
+                "reward": 0.0,
+                "creation_time": 1733778473.978766,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos-debug/SoccerTwos/SoccerTwos-49499806.pt"
+                ]
+            },
+            {
+                "steps": 49999984,
+                "file_path": "results/SoccerTwos-debug/SoccerTwos/SoccerTwos-49999984.onnx",
+                "reward": 0.0,
+                "creation_time": 1733779189.447673,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos-debug/SoccerTwos/SoccerTwos-49999984.pt"
+                ]
+            },
+            {
+                "steps": 50000036,
+                "file_path": "results/SoccerTwos-debug/SoccerTwos/SoccerTwos-50000036.onnx",
+                "reward": 0.0,
+                "creation_time": 1733779189.6087015,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos-debug/SoccerTwos/SoccerTwos-50000036.pt"
+                ]
+            }
+        ],
+        "elo": 1880.3194419754307,
+        "final_checkpoint": {
+            "steps": 50000036,
+            "file_path": "results/SoccerTwos-debug/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1733779189.6087015,
+            "auxillary_file_paths": [
+                "results/SoccerTwos-debug/SoccerTwos/SoccerTwos-50000036.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.5.1+cu124"
+    }
+}