First Push with larger scale

README.md

@@ -0,0 +1,31 @@
+
+---
+      tags:
+      - unity-ml-agents
+      - ml-agents
+      - deep-reinforcement-learning
+      - reinforcement-learning
+      - ML-Agents-SoccerTwos
+      library_name: ml-agents
+---
+    
+  # **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://github.com/huggingface/ml-agents#get-started
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+
+
+  ### Resume the training
+  ```
+  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. Go to https://huggingface.co/spaces/unity/ML-Agents-SoccerTwos
+  2. Step 1: Write your model_id: jinukoo/poca-SoccerTwos_1
+  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 sha256:142428ca7cf78ab94ffcae2da40d1e6959f2bba00632129d07311dbf07d6723e
+size 2819099

SoccerTwos/SoccerTwos-48499949.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86419b7e7be129516e6344286786cbd5473c79d2dc24c0c99d9063913523f877
+size 2819099

SoccerTwos/SoccerTwos-48499949.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e08b68a73ea7e32b9195ba7e110e3e949ae8a2c2554693911f6e85357b67ff3f
+size 34742297

SoccerTwos/SoccerTwos-48999994.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0b2c99358fc9de0978b8f980e4bf96d1dd75b4468bbb6705843501bd73b057f
+size 2819099

SoccerTwos/SoccerTwos-48999994.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:924c5c430a67cd92f18a69e5eec5350fdc3e93ff8b51a83b016ea612802f33f9
+size 34742297

SoccerTwos/SoccerTwos-49499974.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efaba954292b54dfc484bc304d54e98bd2aacab7531d5fd3bfb7fd5daabe9845
+size 2819099

SoccerTwos/SoccerTwos-49499974.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fcbc8f87a44ebcec9dd4c05459f8465fcf71423aebb1c892b7df39be40e6370
+size 34742297

SoccerTwos/SoccerTwos-49999992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88c4bf880c560506b7039b61a53a9b85b4c5e30085e3db1f268cab708fda65d8
+size 2819099

SoccerTwos/SoccerTwos-49999992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:291ae284d6c2cec8ece4e58df5b0caa58ff42545f186fc5e61194fd7638a8992
+size 34742297

SoccerTwos/SoccerTwos-50000022.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:142428ca7cf78ab94ffcae2da40d1e6959f2bba00632129d07311dbf07d6723e
+size 2819099

SoccerTwos/SoccerTwos-50000022.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:545aca5267341c812ef61212093b2d959010abcec90988d977fdbb4d62a0190a
+size 34742297

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:545aca5267341c812ef61212093b2d959010abcec90988d977fdbb4d62a0190a
+size 34742297

SoccerTwos/events.out.tfevents.1680258703.hodoo-01.11221.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54ce21e08d8261d5d353f919b61fe34de706f4eed2b3353264a3fb8e28b60289
+size 365887

SoccerTwos/events.out.tfevents.1680493648.hodoo-01.22824.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e48008620250ef5451e409eec019ddf9e8a1a47daf3b075c0eccf975825ea8d1
+size 145262

SoccerTwos/events.out.tfevents.1680494095.hodoo-01.23307.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e54082662cc4139d61d07f7055cdf19ebf88868a2e60a3ae0eefd1a44cc6b649
+size 11530343

SoccerTwos/events.out.tfevents.1680514625.hodoo-01.27618.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b414ed8182862832a02ad276854b8284b5e9aed325015554e57a6c10921ceb5
+size 234464

SoccerTwos/events.out.tfevents.1680515075.hodoo-01.27870.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cc294a5742dc34a01d2a6bcb2abb5dbf2803f6198178cac0b8faef9c6bb2e67
+size 38253034

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 4096, "buffer_size": 102400, "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": true, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "resnet", "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": 5000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos_1", "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 +1,82 @@
+default_settings: null
+behaviors:
+  SoccerTwos:
+    trainer_type: poca
+    hyperparameters:
+      batch_size: 4096
+      buffer_size: 102400
+      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: true
+      hidden_units: 512
+      num_layers: 3
+      vis_encode_type: resnet
+      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: 5000
+      window: 10
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/SoccerTwos.x86_64
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  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
+environment_parameters: null
+checkpoint_settings:
+  run_id: SoccerTwos_1
+  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 +1,304 @@
+Mono path[0] = '/home/jinukoo/HFRL/ml-agents/training-envs-executables/SoccerTwos_Data/Managed'
+Mono config path = '/home/jinukoo/HFRL/ml-agents/training-envs-executables/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/jinukoo/HFRL/ml-agents/training-envs-executables/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  0.067 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: 1.302084 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 6 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]: 708286 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.1 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 128 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 300.0 KB
+      Peak Allocated Bytes 249.6 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_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 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 6
+      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 11
+      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_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 0.7 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 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]: 708287 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 4.8 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 708287 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]: 708286 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]: 708287 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]: 708287 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]: 708286 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]: 708287 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]: 708286 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": 1.4850791692733765,
+            "min": 1.4256231784820557,
+            "max": 1.783791422843933,
+            "count": 3771
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 29416.44921875,
+            "min": 17761.49609375,
+            "max": 40767.0703125,
+            "count": 3771
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 79.9672131147541,
+            "min": 49.43434343434343,
+            "max": 117.83333333333333,
+            "count": 3771
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19512.0,
+            "min": 7128.0,
+            "max": 21608.0,
+            "count": 3771
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1630.5199995189128,
+            "min": 1613.6555317266225,
+            "max": 1818.8031434927584,
+            "count": 3771
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 198923.43994130736,
+            "min": 122525.19065368592,
+            "max": 355368.689448794,
+            "count": 3771
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 49999992.0,
+            "min": 12299962.0,
+            "max": 49999992.0,
+            "count": 3771
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 49999992.0,
+            "min": 12299962.0,
+            "max": 49999992.0,
+            "count": 3771
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.016999894753098488,
+            "min": -0.12616680562496185,
+            "max": 0.09603842347860336,
+            "count": 3771
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -2.090986967086792,
+            "min": -20.20294189453125,
+            "max": 13.92557144165039,
+            "count": 3771
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.015765422955155373,
+            "min": -0.12606105208396912,
+            "max": 0.09782852977514267,
+            "count": 3771
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -1.9391469955444336,
+            "min": -19.7592716217041,
+            "max": 14.185136795043945,
+            "count": 3771
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 3771
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 3771
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.03594471865553197,
+            "min": -0.5129999998790115,
+            "max": 0.4166758603063123,
+            "count": 3771
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -4.421200394630432,
+            "min": -68.74199998378754,
+            "max": 60.41799974441528,
+            "count": 3771
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.03594471865553197,
+            "min": -0.5129999998790115,
+            "max": 0.4166758603063123,
+            "count": 3771
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -4.421200394630432,
+            "min": -68.74199998378754,
+            "max": 60.41799974441528,
+            "count": 3771
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 3771
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 3771
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.01985647118766792,
+            "min": 0.014973752333705003,
+            "max": 0.022444916989964744,
+            "count": 367
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.01985647118766792,
+            "min": 0.014973752333705003,
+            "max": 0.022444916989964744,
+            "count": 367
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.07494918862978617,
+            "min": 0.06786443119247755,
+            "max": 0.09158067335685094,
+            "count": 367
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.07494918862978617,
+            "min": 0.06786443119247755,
+            "max": 0.09158067335685094,
+            "count": 367
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.07917612830797831,
+            "min": 0.07220904245972633,
+            "max": 0.09506003459294637,
+            "count": 367
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.07917612830797831,
+            "min": 0.07220904245972633,
+            "max": 0.09506003459294637,
+            "count": 367
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.00030000000000000003,
+            "min": 0.00030000000000000003,
+            "max": 0.00030000000000000003,
+            "count": 367
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.00030000000000000003,
+            "min": 0.00030000000000000003,
+            "max": 0.00030000000000000003,
+            "count": 367
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.19999999999999996,
+            "min": 0.19999999999999996,
+            "max": 0.19999999999999996,
+            "count": 367
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.19999999999999996,
+            "min": 0.19999999999999996,
+            "max": 0.19999999999999996,
+            "count": 367
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005,
+            "min": 0.005,
+            "max": 0.005,
+            "count": 367
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005,
+            "min": 0.005,
+            "max": 0.005,
+            "count": 367
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1680515074",
+        "python_version": "3.9.16 (main, Mar  8 2023, 14:00:05) \n[GCC 11.2.0]",
+        "command_line_arguments": "/home/jinukoo/anaconda3/envs/soccer/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos_1 --no-graphics --resume",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.11.0+cu102",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1680584114"
+    },
+    "total": 69039.51107467618,
+    "count": 1,
+    "self": 0.27026671217754483,
+    "children": {
+        "run_training.setup": {
+            "total": 0.008927013259381056,
+            "count": 1,
+            "self": 0.008927013259381056
+        },
+        "TrainerController.start_learning": {
+            "total": 69039.23188095074,
+            "count": 1,
+            "self": 46.88477434264496,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 3.7687600338831544,
+                    "count": 77,
+                    "self": 3.7687600338831544
+                },
+                "TrainerController.advance": {
+                    "total": 68988.34327531932,
+                    "count": 2567990,
+                    "self": 43.6723068789579,
+                    "children": {
+                        "env_step": {
+                            "total": 54392.1399778761,
+                            "count": 2567990,
+                            "self": 43929.67047391925,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 10436.666205249261,
+                                    "count": 2567990,
+                                    "self": 282.74313431978226,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 10153.923070929479,
+                                            "count": 4721936,
+                                            "self": 10153.923070929479
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 25.803298707585782,
+                                    "count": 2567990,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 68924.02226980822,
+                                            "count": 2567990,
+                                            "is_parallel": true,
+                                            "self": 31104.854727547616,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.002117745578289032,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.000569462776184082,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.00154828280210495,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00154828280210495
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.029935280792415142,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005185911431908607,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0004728552885353565,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004728552885353565
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.02732711425051093,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.02732711425051093
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0016167201101779938,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003783875145018101,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0012383325956761837,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0012383325956761837
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.23856165912002325,
+                                                    "count": 152,
+                                                    "is_parallel": true,
+                                                    "self": 0.049330131616443396,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.18923152750357985,
+                                                            "count": 608,
+                                                            "is_parallel": true,
+                                                            "self": 0.18923152750357985
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 37818.928980601486,
+                                                    "count": 2567989,
+                                                    "is_parallel": true,
+                                                    "self": 2354.372796281241,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 1501.6758446977474,
+                                                            "count": 2567989,
+                                                            "is_parallel": true,
+                                                            "self": 1501.6758446977474
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 26912.11968277814,
+                                                            "count": 2567989,
+                                                            "is_parallel": true,
+                                                            "self": 26912.11968277814
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 7050.760656844359,
+                                                            "count": 5135978,
+                                                            "is_parallel": true,
+                                                            "self": 1479.640364073217,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 5571.120292771142,
+                                                                    "count": 20543912,
+                                                                    "is_parallel": true,
+                                                                    "self": 5571.120292771142
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 14552.530990564264,
+                            "count": 2567990,
+                            "self": 310.8270340245217,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 6093.4004200175405,
+                                    "count": 2567990,
+                                    "self": 6075.062773200683,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 18.33764681685716,
+                                            "count": 76,
+                                            "self": 18.33764681685716
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 8148.303536522202,
+                                    "count": 367,
+                                    "self": 5360.714502063114,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 2787.589034459088,
+                                            "count": 27525,
+                                            "self": 2787.589034459088
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 7.599592208862305e-07,
+                    "count": 1,
+                    "self": 7.599592208862305e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.2350704949349165,
+                    "count": 1,
+                    "self": 0.0024241660721600056,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.2326463288627565,
+                            "count": 1,
+                            "self": 0.2326463288627565
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "elo": 1629.8091671728114,
+        "checkpoints": [
+            {
+                "steps": 48499949,
+                "file_path": "results/SoccerTwos_1/SoccerTwos/SoccerTwos-48499949.onnx",
+                "reward": 0.0,
+                "creation_time": 1680581377.819263,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos_1/SoccerTwos/SoccerTwos-48499949.pt"
+                ]
+            },
+            {
+                "steps": 48999994,
+                "file_path": "results/SoccerTwos_1/SoccerTwos/SoccerTwos-48999994.onnx",
+                "reward": 0.0,
+                "creation_time": 1680582277.101221,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos_1/SoccerTwos/SoccerTwos-48999994.pt"
+                ]
+            },
+            {
+                "steps": 49499974,
+                "file_path": "results/SoccerTwos_1/SoccerTwos/SoccerTwos-49499974.onnx",
+                "reward": 0.0,
+                "creation_time": 1680583192.5774992,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos_1/SoccerTwos/SoccerTwos-49499974.pt"
+                ]
+            },
+            {
+                "steps": 49999992,
+                "file_path": "results/SoccerTwos_1/SoccerTwos/SoccerTwos-49999992.onnx",
+                "reward": 0.0,
+                "creation_time": 1680584113.5956023,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos_1/SoccerTwos/SoccerTwos-49999992.pt"
+                ]
+            },
+            {
+                "steps": 50000022,
+                "file_path": "results/SoccerTwos_1/SoccerTwos/SoccerTwos-50000022.onnx",
+                "reward": 0.0,
+                "creation_time": 1680584113.8381567,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos_1/SoccerTwos/SoccerTwos-50000022.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 50000022,
+            "file_path": "results/SoccerTwos_1/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1680584113.8381567,
+            "auxillary_file_paths": [
+                "results/SoccerTwos_1/SoccerTwos/SoccerTwos-50000022.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}