Updated model with more timesteps

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: cmpatino/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 sha256:7251d5ad1bd46d4dd78838966d9198a1003e2de0b9637b384d5997696a5c6f4c
+size 1764633

SoccerTwos/SoccerTwos-10162184.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7251d5ad1bd46d4dd78838966d9198a1003e2de0b9637b384d5997696a5c6f4c
+size 1764633

SoccerTwos/SoccerTwos-10162184.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1344d2347e3fb9a9e188821f80b14dfddeba0e98569f6353771993120b035a9
+size 28421201

SoccerTwos/SoccerTwos-8499987.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60db7110b3676300304572ce2b53e802dc0932d92dc315bc3e4bad5c9d96f482
+size 1764633

SoccerTwos/SoccerTwos-8499987.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8569a738651eecc8330c30b69fcf25a5e88ae98cc7bf562e1561b978100a7233
+size 28421201

SoccerTwos/SoccerTwos-8999992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:772c5ba24d85be361241720cf64e393d1e90c8e014edc8375b994be2ff1a4e60
+size 1764633

SoccerTwos/SoccerTwos-8999992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbfa639a40b754d78f8c2f5a40d3bccc0e74d3b89491eb6bb6db3ba20d41fdc3
+size 28421201

SoccerTwos/SoccerTwos-9499937.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa4e3ef892c12f2f3a67a79a4c076c1f0a2beff220f7bdd47e78c6706155a8bc
+size 1764633

SoccerTwos/SoccerTwos-9499937.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bbac824feb345b611d592e241e4b0bf4e8d31759e5728b6feec0230ec124377
+size 28421201

SoccerTwos/SoccerTwos-9999968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f638bf2fefb3e36d67aafb5ef1f3c6e6410035c482c53edc2afc9f05c2178778
+size 1764633

SoccerTwos/SoccerTwos-9999968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c98d7c27e0d7e08b95b8b9af9e850f505d23f43737ff3d051eeb4b2ef6bc0b10
+size 28421201

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1344d2347e3fb9a9e188821f80b14dfddeba0e98569f6353771993120b035a9
+size 28421201

SoccerTwos/events.out.tfevents.1685408465.MacBook-Air-de-Carlos.local.15870.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c8be3a9bce295f6a202132eacd77eb96c275d14573e292f6ea799f2a580d2a1
+size 2767919

SoccerTwos/events.out.tfevents.1685467256.MacBook-Air-de-Carlos.local.20732.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cb1d1347dcfd2f1a085ee326a7605b3a88a2c492667b0706e4ae3c84384d906
+size 7113271

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.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: 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.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 +1,288 @@
+Mono path[0] = '/Users/cmpatino/Projects/hf-rl/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/Resources/Data/Managed'
+Mono config path = '/Users/cmpatino/Projects/hf-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/cmpatino/Projects/hf-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  0.090 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: 0.979541 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Thread 0x16ebab000 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]: 130122 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 143 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 0.7 KB
+      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 6
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 130123 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 5.0 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 130123 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]: 130122 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]: 130123 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]: 130123 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]: 130122 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]: 130123 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]: 130122 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": 1.5572160482406616,
+            "min": 1.4796764850616455,
+            "max": 2.316222667694092,
+            "count": 692
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 32439.92578125,
+            "min": 19549.421875,
+            "max": 51443.2890625,
+            "count": 692
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 60.79012345679013,
+            "min": 37.40816326530612,
+            "max": 112.68888888888888,
+            "count": 692
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19696.0,
+            "min": 7332.0,
+            "max": 20892.0,
+            "count": 692
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1532.850168432362,
+            "min": 1393.8570641808913,
+            "max": 1556.063024196752,
+            "count": 692
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 248321.72728604265,
+            "min": 136472.0477161022,
+            "max": 363256.00183768506,
+            "count": 692
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 10159890.0,
+            "min": 3249918.0,
+            "max": 10159890.0,
+            "count": 692
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 10159890.0,
+            "min": 3249918.0,
+            "max": 10159890.0,
+            "count": 692
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.017411012202501297,
+            "min": -0.11417428404092789,
+            "max": 0.15166069567203522,
+            "count": 692
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -2.8031728267669678,
+            "min": -22.35116958618164,
+            "max": 24.698177337646484,
+            "count": 692
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.021648546680808067,
+            "min": -0.11651396751403809,
+            "max": 0.1547374129295349,
+            "count": 692
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -3.4854159355163574,
+            "min": -22.662694931030273,
+            "max": 25.887794494628906,
+            "count": 692
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 692
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 692
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.08805714334760394,
+            "min": -0.31483267262430475,
+            "max": 0.3760611441484682,
+            "count": 692
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -14.177200078964233,
+            "min": -66.06939989328384,
+            "max": 63.40679979324341,
+            "count": 692
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.08805714334760394,
+            "min": -0.31483267262430475,
+            "max": 0.3760611441484682,
+            "count": 692
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -14.177200078964233,
+            "min": -66.06939989328384,
+            "max": 63.40679979324341,
+            "count": 692
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 692
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 692
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.019116126811907937,
+            "min": 0.009264162741116404,
+            "max": 0.023554403986781835,
+            "count": 335
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.019116126811907937,
+            "min": 0.009264162741116404,
+            "max": 0.023554403986781835,
+            "count": 335
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.10319636215766272,
+            "min": 0.07646674041946729,
+            "max": 0.1312625450392564,
+            "count": 335
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.10319636215766272,
+            "min": 0.07646674041946729,
+            "max": 0.1312625450392564,
+            "count": 335
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.10433849568168323,
+            "min": 0.07763358304897944,
+            "max": 0.13379605958859125,
+            "count": 335
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.10433849568168323,
+            "min": 0.07763358304897944,
+            "max": 0.13379605958859125,
+            "count": 335
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 335
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 335
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 335
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 335
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 335
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 335
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1685467254",
+        "python_version": "3.9.16 (main, Mar  8 2023, 04:29:24) \n[Clang 14.0.6 ]",
+        "command_line_arguments": "/Users/cmpatino/Software/miniconda3/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": "1685492584"
+    },
+    "total": 24436.345536667002,
+    "count": 1,
+    "self": 0.29455254100321326,
+    "children": {
+        "run_training.setup": {
+            "total": 0.013618209000000103,
+            "count": 1,
+            "self": 0.013618209000000103
+        },
+        "TrainerController.start_learning": {
+            "total": 24436.037365917,
+            "count": 1,
+            "self": 5.864208124992729,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.8453661679947158,
+                    "count": 36,
+                    "self": 2.8453661679947158
+                },
+                "TrainerController.advance": {
+                    "total": 24427.21861583201,
+                    "count": 483364,
+                    "self": 5.138009383848839,
+                    "children": {
+                        "env_step": {
+                            "total": 18952.890719426316,
+                            "count": 483364,
+                            "self": 18194.754368307887,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 754.6493575943163,
+                                    "count": 483364,
+                                    "self": 20.78563564614217,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 733.8637219481741,
+                                            "count": 867500,
+                                            "self": 733.8637219481741
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 3.4869935241127905,
+                                    "count": 483363,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 24425.90537473736,
+                                            "count": 483363,
+                                            "is_parallel": true,
+                                            "self": 6859.6228179850405,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.054453288007503264,
+                                                    "count": 72,
+                                                    "is_parallel": true,
+                                                    "self": 0.00580904101556956,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.048644246991933704,
+                                                            "count": 288,
+                                                            "is_parallel": true,
+                                                            "self": 0.048644246991933704
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 17566.22810346431,
+                                                    "count": 483363,
+                                                    "is_parallel": true,
+                                                    "self": 50.10850966785438,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 318.4643417006471,
+                                                            "count": 483363,
+                                                            "is_parallel": true,
+                                                            "self": 318.4643417006471
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 16486.666769027204,
+                                                            "count": 483363,
+                                                            "is_parallel": true,
+                                                            "self": 16486.666769027204
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 710.988483068601,
+                                                            "count": 966726,
+                                                            "is_parallel": true,
+                                                            "self": 75.7151926292131,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 635.2732904393879,
+                                                                    "count": 3866904,
+                                                                    "is_parallel": true,
+                                                                    "self": 635.2732904393879
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 5469.1898870218465,
+                            "count": 483363,
+                            "self": 38.61935983038529,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 1201.0461626584283,
+                                    "count": 483363,
+                                    "self": 1199.561214450426,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 1.484948208002379,
+                                            "count": 14,
+                                            "self": 1.484948208002379
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 4229.524364533033,
+                                    "count": 336,
+                                    "self": 530.0860378200996,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 3699.4383267129333,
+                                            "count": 10080,
+                                            "self": 3699.4383267129333
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 4.169996827840805e-07,
+                    "count": 1,
+                    "self": 4.169996827840805e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.1091753750006319,
+                    "count": 1,
+                    "self": 0.0029110840005159844,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.10626429100011592,
+                            "count": 1,
+                            "self": 0.10626429100011592
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 8499987,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8499987.onnx",
+                "reward": 0.0,
+                "creation_time": 1685486721.939116,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8499987.pt"
+                ]
+            },
+            {
+                "steps": 8999992,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8999992.onnx",
+                "reward": 0.0,
+                "creation_time": 1685488504.198619,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8999992.pt"
+                ]
+            },
+            {
+                "steps": 9499937,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-9499937.onnx",
+                "reward": 0.0,
+                "creation_time": 1685490258.5190568,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-9499937.pt"
+                ]
+            },
+            {
+                "steps": 9999968,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-9999968.onnx",
+                "reward": 0.0,
+                "creation_time": 1685492017.968396,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-9999968.pt"
+                ]
+            },
+            {
+                "steps": 10162184,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-10162184.onnx",
+                "reward": 0.0,
+                "creation_time": 1685492584.673598,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-10162184.pt"
+                ]
+            }
+        ],
+        "elo": 1529.6803936013202,
+        "final_checkpoint": {
+            "steps": 10162184,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1685492584.673598,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-10162184.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0"
+    }
+}