v1

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: davidhajdu/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:e014b843f7fda294ac9502ea8779a02d712e87b1ba3807bedcd07129c2c93a45
+size 1764633

SoccerTwos/SoccerTwos-1999908.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f53f97c401792d92a97f795d00a1ca0d31af78f2f7a6725f7eba63092bfd5b4e
+size 1764633

SoccerTwos/SoccerTwos-1999908.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a2cc2ccef458bc1bff788f2f353208585a84f1264a837ae55141de6992e20ed
+size 28421201

SoccerTwos/SoccerTwos-2499998.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9528190596de9482fd11c32d0e06a6a8637f497cd8e76ee6219141977debb1b7
+size 1764633

SoccerTwos/SoccerTwos-2499998.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d3e87ce2ed6ee9d378945f3b50cb2107c78a4d2d75f69b74f27e9a8b8dd86f2
+size 28421201

SoccerTwos/SoccerTwos-2795762.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f358da918edcd4a8959522a6d0f12cfc04c96db561da363f4362335824555fc
+size 1764633

SoccerTwos/SoccerTwos-2795762.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe5df99d3c0d96aaf22d00c7ce62fb65e87dd9b7ff8ef6a266e3fb123f80ef8f
+size 28421201

SoccerTwos/SoccerTwos-2999994.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7faf31661f71902e04771cec3f02c3fa5a720dc80c3668c7830f4a53d7e240
+size 1764633

SoccerTwos/SoccerTwos-2999994.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34569aa75066a9bbc6812855cdf434a66812101d8654f402027c646732c83e87
+size 28421201

SoccerTwos/SoccerTwos-3010534.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e014b843f7fda294ac9502ea8779a02d712e87b1ba3807bedcd07129c2c93a45
+size 1764633

SoccerTwos/SoccerTwos-3010534.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d2a1677003d4cefff2179c679ab9211e309437e439ac129126aa03de795e3dd
+size 28421201

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d2a1677003d4cefff2179c679ab9211e309437e439ac129126aa03de795e3dd
+size 28421201

SoccerTwos/events.out.tfevents.1675384736.Davids-MacBook-Pro.local.25482.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9bd267c841335bd39cada1315b74ae7b305570ab36fbb47e74227c3dbfb36bd
+size 1193

SoccerTwos/events.out.tfevents.1675384783.Davids-MacBook-Pro.local.25574.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e2034890f1ef3f40be2093d339b3c8ee1de569d1223962f8082aad81265c98f
+size 244557

SoccerTwos/events.out.tfevents.1675452037.Davids-MacBook-Pro.local.20342.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70be28026438c8d9111cc95488d6e1a9c82cd1fdd79aa0f9213141b565222412
+size 2082527

SoccerTwos/events.out.tfevents.1675468325.Davids-MacBook-Pro.local.22275.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d6048e4522da8826a2f19cc19a557a260ae4fc1c26fb29523bbcd64d2f62131
+size 227073

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 50000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos/SoccerTwos", "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: 50000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 50000
+      team_change: 200000
+      swap_steps: 2000
+      window: 10
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/SoccerTwos/SoccerTwos
+  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 +1,288 @@
+Mono path[0] = '/Users/davidhajdu/Desktop/projects/RL/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/Resources/Data/Managed'
+Mono config path = '/Users/davidhajdu/Desktop/projects/RL/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/davidhajdu/Desktop/projects/RL/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  0.096 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: 0.465583 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Thread 0x16e7d3000 may have been prematurely finalized
+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]: 4056 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.1 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 150 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 78.8 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 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 0.7 KB
+      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 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]: 4057 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]: 4057 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]: 4056 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]: 4057 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]: 4057 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]: 4056 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 3.4 MB
+      Peak Large allocation bytes 0 B
+[ALLOC_TYPETREE] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 4057 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]: 4056 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": 2.25303316116333,
+            "min": 2.2181384563446045,
+            "max": 2.333526849746704,
+            "count": 22
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 47223.57421875,
+            "min": 21176.81640625,
+            "max": 49540.0234375,
+            "count": 22
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 58.588235294117645,
+            "min": 42.55102040816327,
+            "max": 75.10606060606061,
+            "count": 22
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19920.0,
+            "min": 8340.0,
+            "max": 20180.0,
+            "count": 22
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1436.6850885574333,
+            "min": 1420.957679346875,
+            "max": 1445.1289760810987,
+            "count": 22
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 244236.46505476366,
+            "min": 139478.1277144495,
+            "max": 283061.4419381178,
+            "count": 22
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 3009978.0,
+            "min": 2799997.0,
+            "max": 3009978.0,
+            "count": 22
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 3009978.0,
+            "min": 2799997.0,
+            "max": 3009978.0,
+            "count": 22
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.04858648031949997,
+            "min": -0.06071087345480919,
+            "max": 0.057406455278396606,
+            "count": 22
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -8.211114883422852,
+            "min": -8.211114883422852,
+            "max": 9.586877822875977,
+            "count": 22
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.051111526787281036,
+            "min": -0.05901632457971573,
+            "max": 0.05398515984416008,
+            "count": 22
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -8.637847900390625,
+            "min": -8.637847900390625,
+            "max": 9.015522003173828,
+            "count": 22
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 22
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 22
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.08056568252969776,
+            "min": -0.270185566440071,
+            "max": 0.22813404525848144,
+            "count": 22
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -13.615600347518921,
+            "min": -26.20799994468689,
+            "max": 42.88920050859451,
+            "count": 22
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.08056568252969776,
+            "min": -0.270185566440071,
+            "max": 0.22813404525848144,
+            "count": 22
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -13.615600347518921,
+            "min": -26.20799994468689,
+            "max": 42.88920050859451,
+            "count": 22
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 22
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 22
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.01866164224144692,
+            "min": 0.013299963200309625,
+            "max": 0.021053528459742666,
+            "count": 10
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.01866164224144692,
+            "min": 0.013299963200309625,
+            "max": 0.021053528459742666,
+            "count": 10
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.1034640853603681,
+            "min": 0.08911226640144984,
+            "max": 0.10452298521995544,
+            "count": 10
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.1034640853603681,
+            "min": 0.08911226640144984,
+            "max": 0.10452298521995544,
+            "count": 10
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.10537167390187581,
+            "min": 0.09102364853024483,
+            "max": 0.10614525328079859,
+            "count": 10
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.10537167390187581,
+            "min": 0.09102364853024483,
+            "max": 0.10614525328079859,
+            "count": 10
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 10
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 10
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 10
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 10
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 10
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 10
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1675468324",
+        "python_version": "3.10.4 (main, Jan 23 2023, 21:59:58) [Clang 14.0.0 (clang-1400.0.29.202)]",
+        "command_line_arguments": "/Users/davidhajdu/.pyenv/versions/RL/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos --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": "1675469777"
+    },
+    "total": 1452.8753001250006,
+    "count": 1,
+    "self": 0.15392699999938486,
+    "children": {
+        "run_training.setup": {
+            "total": 0.01425879199814517,
+            "count": 1,
+            "self": 0.01425879199814517
+        },
+        "TrainerController.start_learning": {
+            "total": 1452.7071143330031,
+            "count": 1,
+            "self": 0.1983301609288901,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.8846464169982937,
+                    "count": 3,
+                    "self": 1.8846464169982937
+                },
+                "TrainerController.advance": {
+                    "total": 1450.4863115880798,
+                    "count": 14970,
+                    "self": 0.19549912325965124,
+                    "children": {
+                        "env_step": {
+                            "total": 1227.144114718143,
+                            "count": 14970,
+                            "self": 1196.0092934863278,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 31.00468764469042,
+                                    "count": 14970,
+                                    "self": 0.9640196857399133,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 30.040667958950507,
+                                            "count": 27044,
+                                            "self": 30.040667958950507
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.13013358712487388,
+                                    "count": 14969,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 1450.3859152803452,
+                                            "count": 14969,
+                                            "is_parallel": true,
+                                            "self": 283.8744217774729,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.007310874996619532,
+                                                    "count": 6,
+                                                    "is_parallel": true,
+                                                    "self": 0.0009484170041105244,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.0063624579925090075,
+                                                            "count": 24,
+                                                            "is_parallel": true,
+                                                            "self": 0.0063624579925090075
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1166.5041826278757,
+                                                    "count": 14969,
+                                                    "is_parallel": true,
+                                                    "self": 2.887594155909028,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 20.931710134133027,
+                                                            "count": 14969,
+                                                            "is_parallel": true,
+                                                            "self": 20.931710134133027
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1102.4025346820818,
+                                                            "count": 14969,
+                                                            "is_parallel": true,
+                                                            "self": 1102.4025346820818
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 40.2823436557519,
+                                                            "count": 29938,
+                                                            "is_parallel": true,
+                                                            "self": 4.493868864137767,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 35.788474791614135,
+                                                                    "count": 119752,
+                                                                    "is_parallel": true,
+                                                                    "self": 35.788474791614135
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 223.1466977466771,
+                            "count": 14969,
+                            "self": 1.5573225504122092,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 55.09537353026826,
+                                    "count": 14969,
+                                    "self": 54.94132548926791,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.15404804100035108,
+                                            "count": 1,
+                                            "self": 0.15404804100035108
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 166.49400166599662,
+                                    "count": 10,
+                                    "self": 27.522364000957168,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 138.97163766503945,
+                                            "count": 300,
+                                            "self": 138.97163766503945
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 7.089984137564898e-07,
+                    "count": 1,
+                    "self": 7.089984137564898e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.1378254579976783,
+                    "count": 1,
+                    "self": 0.0016826239952933975,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.13614283400238492,
+                            "count": 1,
+                            "self": 0.13614283400238492
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0"
+    },
+    "SoccerTwos": {
+        "elo": 1436.6847581340735,
+        "checkpoints": [
+            {
+                "steps": 1999908,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-1999908.onnx",
+                "reward": 0.0,
+                "creation_time": 1675462936.519731,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-1999908.pt"
+                ]
+            },
+            {
+                "steps": 2499998,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-2499998.onnx",
+                "reward": 0.0,
+                "creation_time": 1675466274.472631,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-2499998.pt"
+                ]
+            },
+            {
+                "steps": 2795762,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-2795762.onnx",
+                "reward": 0.0,
+                "creation_time": 1675468268.3589702,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-2795762.pt"
+                ]
+            },
+            {
+                "steps": 2999994,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-2999994.onnx",
+                "reward": 0.0,
+                "creation_time": 1675469694.2305589,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-2999994.pt"
+                ]
+            },
+            {
+                "steps": 3010534,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3010534.onnx",
+                "reward": 0.0,
+                "creation_time": 1675469776.965055,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-3010534.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 3010534,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1675469776.965055,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-3010534.pt"
+            ]
+        }
+    }
+}