Rock n roll

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: bjarlestam/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:f25bb417690224bd8375ddc863f66f35de30d35231b9de51e69fe7cbdb9bf204
+size 2815689

SoccerTwos/SoccerTwos-331652.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f25bb417690224bd8375ddc863f66f35de30d35231b9de51e69fe7cbdb9bf204
+size 2815689

SoccerTwos/SoccerTwos-331652.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7e902c9997bb4e54ab800e41aa2ea801efe536c07bddc1071c862898d4dc20e
+size 34728689

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7e902c9997bb4e54ab800e41aa2ea801efe536c07bddc1071c862898d4dc20e
+size 34728689

SoccerTwos/events.out.tfevents.1683405464.CLM-FVFF611QQ05P.local.34842.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03b292a5080760f2bc9dc7004b129071a86ac670c769d9d044e7f2f2614537d4
+size 253740

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0002, "beta": 0.01, "epsilon": 0.25, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 2000000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.973, "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": 5000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 200000, "team_change": 200000, "swap_steps": 2000, "window": 50, "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": false, "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: 0.0002
+      beta: 0.01
+      epsilon: 0.25
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: constant
+      beta_schedule: constant
+      epsilon_schedule: constant
+    checkpoint_interval: 2000000
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 3
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.973
+        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: 5000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 200000
+      team_change: 200000
+      swap_steps: 2000
+      window: 50
+      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: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,421 @@
+Mono path[0] = '/Users/andreas.bjarlestam/projects/machinelearning_stuff/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/Resources/Data/Managed'
+Mono config path = '/Users/andreas.bjarlestam/projects/machinelearning_stuff/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/andreas.bjarlestam/projects/machinelearning_stuff/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  0.055 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: 0.399125 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+GRPC Exception: Status(StatusCode=Unknown, Detail="Exception calling application: [Errno 32] Broken pipe"). Disconnecting from trainer.
+Thread 0x16ec2b000 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]: 6428 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 169 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 78.9 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 0.7 KB
+      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 2
+    [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]: 6429 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]: 6429 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]: 6428 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]: 6429 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]: 6429 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]: 6428 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]: 6429 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]: 6428 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 +1,361 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 3.2537543773651123,
+            "min": 3.2069151401519775,
+            "max": 3.2958173751831055,
+            "count": 33
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 58411.3984375,
+            "min": 24713.4296875,
+            "max": 105466.15625,
+            "count": 33
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 818.0,
+            "min": 447.0,
+            "max": 999.0,
+            "count": 33
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19632.0,
+            "min": 1788.0,
+            "max": 31856.0,
+            "count": 33
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1209.357611408545,
+            "min": 1199.2393548497907,
+            "max": 1209.357611408545,
+            "count": 32
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 7256.14566845127,
+            "min": 2398.4787096995815,
+            "max": 16919.769407736774,
+            "count": 32
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 329724.0,
+            "min": 9770.0,
+            "max": 329724.0,
+            "count": 33
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 329724.0,
+            "min": 9770.0,
+            "max": 329724.0,
+            "count": 33
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": 0.0030621204059571028,
+            "min": -0.0008333418518304825,
+            "max": 0.07384230196475983,
+            "count": 33
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": 0.03674544394016266,
+            "min": -0.015000153332948685,
+            "max": 1.03379225730896,
+            "count": 33
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.0016769192880019546,
+            "min": -0.0017020993400365114,
+            "max": 0.07384181767702103,
+            "count": 33
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 0.020123030990362167,
+            "min": -0.03063778765499592,
+            "max": 1.0337854623794556,
+            "count": 33
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 33
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 33
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.10413333773612976,
+            "min": -0.42857142857142855,
+            "max": 0.1590666671593984,
+            "count": 33
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -1.2496000528335571,
+            "min": -6.0,
+            "max": 1.9088000059127808,
+            "count": 33
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.10413333773612976,
+            "min": -0.42857142857142855,
+            "max": 0.1590666671593984,
+            "count": 33
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -1.2496000528335571,
+            "min": -6.0,
+            "max": 1.9088000059127808,
+            "count": 33
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 33
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 33
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.017120584277048087,
+            "min": 0.01184630231000483,
+            "max": 0.020048254150606227,
+            "count": 15
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.017120584277048087,
+            "min": 0.01184630231000483,
+            "max": 0.020048254150606227,
+            "count": 15
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.0025950087544818717,
+            "min": 0.0006825556454714387,
+            "max": 0.004943428281694651,
+            "count": 15
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.0025950087544818717,
+            "min": 0.0006825556454714387,
+            "max": 0.004943428281694651,
+            "count": 15
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.002597692298392455,
+            "min": 0.0006826190966724728,
+            "max": 0.0050204995010669036,
+            "count": 15
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.002597692298392455,
+            "min": 0.0006826190966724728,
+            "max": 0.0050204995010669036,
+            "count": 15
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.00019999999999999996,
+            "min": 0.00019999999999999996,
+            "max": 0.00020000000000000004,
+            "count": 15
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.00019999999999999996,
+            "min": 0.00019999999999999996,
+            "max": 0.00020000000000000004,
+            "count": 15
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.25,
+            "min": 0.25,
+            "max": 0.25,
+            "count": 15
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.25,
+            "min": 0.25,
+            "max": 0.25,
+            "count": 15
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.010000000000000002,
+            "min": 0.01,
+            "max": 0.010000000000000002,
+            "count": 15
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.010000000000000002,
+            "min": 0.01,
+            "max": 0.010000000000000002,
+            "count": 15
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1683405461",
+        "python_version": "3.9.16 | packaged by conda-forge | (main, Feb  1 2023, 21:38:11) \n[Clang 14.0.6 ]",
+        "command_line_arguments": "/Users/andreas.bjarlestam/mambaforge/envs/huggingface-rl-course/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics",
+        "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": "1683406974"
+    },
+    "total": 1512.703789291,
+    "count": 1,
+    "self": 0.1597869570000512,
+    "children": {
+        "run_training.setup": {
+            "total": 0.05548366699999985,
+            "count": 1,
+            "self": 0.05548366699999985
+        },
+        "TrainerController.start_learning": {
+            "total": 1512.4885186669999,
+            "count": 1,
+            "self": 0.25970882700585207,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.2931211249999333,
+                    "count": 2,
+                    "self": 2.2931211249999333
+                },
+                "TrainerController.advance": {
+                    "total": 1509.782210796994,
+                    "count": 21579,
+                    "self": 0.24726577001251826,
+                    "children": {
+                        "env_step": {
+                            "total": 1238.8051764919874,
+                            "count": 21579,
+                            "self": 1195.3630238779756,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 43.25285580400478,
+                                    "count": 21579,
+                                    "self": 1.2754701040110632,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 41.97738569999372,
+                                            "count": 42860,
+                                            "self": 41.97738569999372
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.1892968100068888,
+                                    "count": 21578,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 1509.6495894130055,
+                                            "count": 21578,
+                                            "is_parallel": true,
+                                            "self": 349.4384122730048,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.0037250000000343952,
+                                                    "count": 4,
+                                                    "is_parallel": true,
+                                                    "self": 0.0005595840002534658,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.0031654159997809295,
+                                                            "count": 16,
+                                                            "is_parallel": true,
+                                                            "self": 0.0031654159997809295
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1160.2074521400007,
+                                                    "count": 21578,
+                                                    "is_parallel": true,
+                                                    "self": 3.0327681719870725,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 20.090124248995796,
+                                                            "count": 21578,
+                                                            "is_parallel": true,
+                                                            "self": 20.090124248995796
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1094.6483185990135,
+                                                            "count": 21578,
+                                                            "is_parallel": true,
+                                                            "self": 1094.6483185990135
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 42.43624112000441,
+                                                            "count": 43156,
+                                                            "is_parallel": true,
+                                                            "self": 4.705739092995032,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 37.73050202700938,
+                                                                    "count": 172624,
+                                                                    "is_parallel": true,
+                                                                    "self": 37.73050202700938
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 270.7297685349941,
+                            "count": 21578,
+                            "self": 2.1676305409926613,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 37.25934370100136,
+                                    "count": 21578,
+                                    "self": 37.25934370100136
+                                },
+                                "_update_policy": {
+                                    "total": 231.30279429300006,
+                                    "count": 15,
+                                    "self": 29.242100787998396,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 202.06069350500167,
+                                            "count": 462,
+                                            "self": 202.06069350500167
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 5.840001904289238e-07,
+                    "count": 1,
+                    "self": 5.840001904289238e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.15347733399994468,
+                    "count": 1,
+                    "self": 0.005591333999973358,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.14788599999997132,
+                            "count": 1,
+                            "self": 0.14788599999997132
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,30 @@
+{
+    "SoccerTwos": {
+        "elo": 1212.4032246556544,
+        "checkpoints": [
+            {
+                "steps": 331652,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-331652.onnx",
+                "reward": 0.0,
+                "creation_time": 1683406974.434873,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-331652.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 331652,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1683406974.434873,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-331652.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0"
+    }
+}