40M steps

.DS_Store

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:736c66aa0fb3dacf50a063ce7fca629939652076fd20b2e6e94130805878c3aa
+size 6148

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+.DS_Store filter=lfs diff=lfs merge=lfs -text

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: atorre/poca-SoccerTwos-40M
+  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:aa185dc5972cd68bede6d71e1ac08f71531894db463346d9648334cdd197c580
+size 1764633

SoccerTwos/SoccerTwos-38499986.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6a161d6487eb6fea6aaf77b1e93df5ef101abd8881919d778b6f1a107d2b49c
+size 1764633

SoccerTwos/SoccerTwos-38499986.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db0389698aa6a9df8dc55f5ed53bba6c40cd4068d23d566e51231026ad53f607
+size 28421201

SoccerTwos/SoccerTwos-38999912.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:557ad360ecce79be60eeba8385b556698cae06f68fc698000de052cabc5f0e29
+size 1764633

SoccerTwos/SoccerTwos-38999912.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b3f5195e539ded689c3c8d1008a1033f02daf9170ad14deb69c3dc92f9b7f5e
+size 28421201

SoccerTwos/SoccerTwos-39499902.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4aee418090b9bf2bf642a9e05ec52a8f820b145a2b71c710e0a25e7042f5cd5
+size 1764633

SoccerTwos/SoccerTwos-39499902.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecdb245329b6e2a4d9d393669f04dd8291913b5e1f0e1f8af3fb4d020fa504f3
+size 28421201

SoccerTwos/SoccerTwos-39999989.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa185dc5972cd68bede6d71e1ac08f71531894db463346d9648334cdd197c580
+size 1764633

SoccerTwos/SoccerTwos-39999989.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cbaeada572aab049e544e97ed87cf21f3fe1c83d7f85a7ab45b2a03911df5f0
+size 28421201

SoccerTwos/SoccerTwos-40000050.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa185dc5972cd68bede6d71e1ac08f71531894db463346d9648334cdd197c580
+size 1764633

SoccerTwos/SoccerTwos-40000050.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bb1983dd7f418825a0106074980db389e9dcf3cc89a621a90f285c7549effec
+size 28421201

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bb1983dd7f418825a0106074980db389e9dcf3cc89a621a90f285c7549effec
+size 28421201

SoccerTwos/events.out.tfevents.1675875266.Alessandros-MBP.fritz.box.22240.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10444ccbf3de85129fea1be8acb09a6940c87fcbbd94cfc71c4489e9441a18c1
+size 9427011

SoccerTwos/events.out.tfevents.1675929529.Alessandros-MBP.fritz.box.25179.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3f2fcdf35d91b9dbfbfb23d7f6d8904cb57fd40e4bcde5b9b6152ba3e8ab067
+size 1193

SoccerTwos/events.out.tfevents.1675929583.Alessandros-MBP.fritz.box.25192.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b9add6ef30e6d067ba86e6e4c2208eb46bd7603e1ee7550596ca2162a63056d
+size 10279003

SoccerTwos/events.out.tfevents.1675970528.Alessandros-MBP.fritz.box.25996.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15c3d182fda6233b7ddaf4c773a2b9bcd0e5a0dcfdb43156ce7e17917852f64b
+size 10279003

SoccerTwos/events.out.tfevents.1676013013.Alessandros-MBP.fritz.box.27120.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38098c24774b1fb4dc23a0cf9687452b48d921bf2a36ebb100a31ef23e2ee80a
+size 10279003

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": 40000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 70000, "team_change": 250000, "swap_steps": 3000, "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, "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", "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: 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: 40000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 70000
+      team_change: 250000
+      swap_steps: 3000
+      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
+  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
+  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 +1,287 @@
+Mono path[0] = '/Users/sasha/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/Resources/Data/Managed'
+Mono config path = '/Users/sasha/ml-agents/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/sasha/ml-agents/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  0.173 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: 0.815581 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Setting up 4 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]: 188087 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 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 0.7 KB
+      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 4
+      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 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 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_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 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_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 4
+    [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]: 188088 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 4.9 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 188088 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.4 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]: 188087 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]: 188088 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]: 188088 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]: 188087 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 3.0 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]: 188088 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]: 188087 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": 1.420534610748291,
+            "min": 1.3608125448226929,
+            "max": 1.570000410079956,
+            "count": 1000
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 28047.03515625,
+            "min": 24803.060546875,
+            "max": 35913.1640625,
+            "count": 1000
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 55.12359550561798,
+            "min": 44.77570093457944,
+            "max": 108.17391304347827,
+            "count": 1000
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19624.0,
+            "min": 18428.0,
+            "max": 21000.0,
+            "count": 1000
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1878.768103515365,
+            "min": 1795.837418342268,
+            "max": 1901.145235982328,
+            "count": 1000
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 334420.722425735,
+            "min": 171269.35675982942,
+            "max": 404701.20162605366,
+            "count": 1000
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 39999989.0,
+            "min": 30009878.0,
+            "max": 39999989.0,
+            "count": 1000
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 39999989.0,
+            "min": 30009878.0,
+            "max": 39999989.0,
+            "count": 1000
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": 0.0312940739095211,
+            "min": -0.14125216007232666,
+            "max": 0.073383629322052,
+            "count": 1000
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": 5.570344924926758,
+            "min": -24.784133911132812,
+            "max": 10.934160232543945,
+            "count": 1000
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.028624339029192924,
+            "min": -0.1449059545993805,
+            "max": 0.07165231555700302,
+            "count": 1000
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 5.095132350921631,
+            "min": -25.281543731689453,
+            "max": 10.67619514465332,
+            "count": 1000
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 1000
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 1000
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.029853929964344154,
+            "min": -0.4508974802594225,
+            "max": 0.3219466656446457,
+            "count": 1000
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 5.313999533653259,
+            "min": -68.66480004787445,
+            "max": 40.91879975795746,
+            "count": 1000
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.029853929964344154,
+            "min": -0.4508974802594225,
+            "max": 0.3219466656446457,
+            "count": 1000
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 5.313999533653259,
+            "min": -68.66480004787445,
+            "max": 40.91879975795746,
+            "count": 1000
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 1000
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 1000
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.016824491468529837,
+            "min": 0.010678941572162632,
+            "max": 0.02459868296670417,
+            "count": 485
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.016824491468529837,
+            "min": 0.010678941572162632,
+            "max": 0.02459868296670417,
+            "count": 485
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.11973893319567044,
+            "min": 0.07159942711393039,
+            "max": 0.12052511448661486,
+            "count": 485
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.11973893319567044,
+            "min": 0.07159942711393039,
+            "max": 0.12052511448661486,
+            "count": 485
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.12087501386801401,
+            "min": 0.07310381432374319,
+            "max": 0.12231633613506952,
+            "count": 485
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.12087501386801401,
+            "min": 0.07310381432374319,
+            "max": 0.12231633613506952,
+            "count": 485
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 485
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 485
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 485
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 485
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 485
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 485
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1676013011",
+        "python_version": "3.9.16 (main, Jan 11 2023, 10:02:19) \n[Clang 14.0.6 ]",
+        "command_line_arguments": "/Users/sasha/opt/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --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",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1676059019"
+    },
+    "total": 43520.903187742,
+    "count": 1,
+    "self": 1.4724713479954517,
+    "children": {
+        "run_training.setup": {
+            "total": 0.026028468999999888,
+            "count": 1,
+            "self": 0.026028468999999888
+        },
+        "TrainerController.start_learning": {
+            "total": 43519.404687925,
+            "count": 1,
+            "self": 16.958283389649296,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 3.045327290983835,
+                    "count": 41,
+                    "self": 3.045327290983835
+                },
+                "TrainerController.advance": {
+                    "total": 43499.19516348536,
+                    "count": 687899,
+                    "self": 18.614015010607545,
+                    "children": {
+                        "env_step": {
+                            "total": 10792.059126881395,
+                            "count": 687899,
+                            "self": 8719.799770878757,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 2061.966871777601,
+                                    "count": 687899,
+                                    "self": 82.47859382463957,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 1979.4882779529617,
+                                            "count": 1253924,
+                                            "self": 1979.4882779529617
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 10.292484225036375,
+                                    "count": 687899,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 43486.1855561065,
+                                            "count": 687899,
+                                            "is_parallel": true,
+                                            "self": 36462.65928638144,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.07384253300281118,
+                                                    "count": 82,
+                                                    "is_parallel": true,
+                                                    "self": 0.016496121003803488,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.057346411999007696,
+                                                            "count": 328,
+                                                            "is_parallel": true,
+                                                            "self": 0.057346411999007696
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 7023.4524271920645,
+                                                    "count": 687899,
+                                                    "is_parallel": true,
+                                                    "self": 436.16573743886875,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 274.88153573949893,
+                                                            "count": 687899,
+                                                            "is_parallel": true,
+                                                            "self": 274.88153573949893
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 5136.899167271001,
+                                                            "count": 687899,
+                                                            "is_parallel": true,
+                                                            "self": 5136.899167271001
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 1175.5059867426962,
+                                                            "count": 1375798,
+                                                            "is_parallel": true,
+                                                            "self": 258.93821506038717,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 916.5677716823091,
+                                                                    "count": 5503192,
+                                                                    "is_parallel": true,
+                                                                    "self": 916.5677716823091
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 32688.52202159336,
+                            "count": 687899,
+                            "self": 130.86425984039306,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 3464.5631697249946,
+                                    "count": 687899,
+                                    "self": 3460.3678304699806,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 4.1953392550142325,
+                                            "count": 20,
+                                            "self": 4.1953392550142325
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 29093.09459202797,
+                                    "count": 485,
+                                    "self": 1479.1673009769256,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 27613.927291051044,
+                                            "count": 14550,
+                                            "self": 27613.927291051044
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 9.840005077421665e-07,
+                    "count": 1,
+                    "self": 9.840005077421665e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.2059127750035259,
+                    "count": 1,
+                    "self": 0.0029265910052345134,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.20298618399829138,
+                            "count": 1,
+                            "self": 0.20298618399829138
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 38499986,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-38499986.onnx",
+                "reward": 0.0,
+                "creation_time": 1676049074.991734,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-38499986.pt"
+                ]
+            },
+            {
+                "steps": 38999912,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-38999912.onnx",
+                "reward": 0.0,
+                "creation_time": 1676051531.274252,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-38999912.pt"
+                ]
+            },
+            {
+                "steps": 39499902,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-39499902.onnx",
+                "reward": 0.0,
+                "creation_time": 1676056719.006643,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-39499902.pt"
+                ]
+            },
+            {
+                "steps": 39999989,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-39999989.onnx",
+                "reward": 0.0,
+                "creation_time": 1676059017.72059,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-39999989.pt"
+                ]
+            },
+            {
+                "steps": 40000050,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-40000050.onnx",
+                "reward": 0.0,
+                "creation_time": 1676059017.946358,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-40000050.pt"
+                ]
+            }
+        ],
+        "elo": 1883.394411941979,
+        "final_checkpoint": {
+            "steps": 40000050,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1676059017.946358,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-40000050.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0"
+    }
+}