First Push`

README.md

@@ -0,0 +1,35 @@
+---
+library_name: ml-agents
+tags:
+- SoccerTwos
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-SoccerTwos
+---
+
+  # **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://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
+
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+  - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
+  browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
+  - A *longer tutorial* to understand how works ML-Agents:
+  https://huggingface.co/learn/deep-rl-course/unit5/introduction
+
+  ### Resume the training
+  ```bash
+  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. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
+  2. Step 1: Find your model_id: giovannidispoto/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 sha256:3dfc2027c8dc413744c2583346f9f67cc0b958d963f7c3780bc48720f85d6d0e
+size 1764633

SoccerTwos/SoccerTwos-0.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6fbc2b2a42e6920baeb456918520a865083e79795b14b5cab8ba0dd84b58e51
+size 1764633

SoccerTwos/SoccerTwos-0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9e354db53a5ab8b92d36e08210944ac57b0d10b2cacaf92a878617a9b8765c7
+size 9478265

SoccerTwos/SoccerTwos-133820.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dfc2027c8dc413744c2583346f9f67cc0b958d963f7c3780bc48720f85d6d0e
+size 1764633

SoccerTwos/SoccerTwos-133820.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5cc5891cb87cfed8ab3ca14ed3028cef8bb1f2e8cfd1db44c1a5be3e19b4271
+size 28421137

SoccerTwos/SoccerTwos-1499744.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62a65db7ff6d04a6ed98aa816f87d221b7a43764db37e3db0e4e3d831c587434
+size 1764633

SoccerTwos/SoccerTwos-1499744.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68cb721c24fb6d52c7d9ef86a8150cfbc0a705c301191bd1c46b4cd183f32892
+size 28421201

SoccerTwos/SoccerTwos-1999130.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c5e2cea75ea7e2fd437d63d1cce80ac4152a23b91b53ff72c9591f4d75d9b96
+size 1764633

SoccerTwos/SoccerTwos-1999130.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1885930fb8def866665a2ba3f301dfeb0192c69e14296599f9456efa499eaaa7
+size 28421201

SoccerTwos/SoccerTwos-2499468.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97c5e44721db83b56b67d431585d7ef223f31d9846a651a23da57c52267918a8
+size 1764633

SoccerTwos/SoccerTwos-2499468.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b7e741047e393067f5b7a9f490918afdd2ef3a3fa37520f35ec4886eee61064
+size 28421201

SoccerTwos/SoccerTwos-499106.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5c922699d0c46e32f7c92f08c14bcb1e74a02b4c508e4ccade5ff8d54d56319
+size 1764633

SoccerTwos/SoccerTwos-499106.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b53b0c923a04dc3644d2e969c1e4befa290a09a6da30128f65c7dd434221c1a
+size 28421201

SoccerTwos/SoccerTwos-999938.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:934235ea93445ea298971e3bc787fdcdab690d119b77093d5bf31e669edd05ce
+size 1764633

SoccerTwos/SoccerTwos-999938.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d1a8ccc1eafc4d3cedccf8af0ad09b6cf7eba32c6c08b49cd099dea77901b99
+size 28421201

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b7e741047e393067f5b7a9f490918afdd2ef3a3fa37520f35ec4886eee61064
+size 28421201

SoccerTwos/events.out.tfevents.1689870507.MBP-di-Giovanni.homenet.telecomitalia.it.24419.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76aedd4763c0bde0f8be2bac06c7711a8aa3e1f9e608ce5df33ed311e1e62676
+size 760367

SoccerTwos/events.out.tfevents.1689924789.MBP-di-Giovanni.homenet.telecomitalia.it.6897.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:311cb6f1c49d3b88ef76ccfba8bd256bc62009f2ba7fba6aa894845f35019004
+size 1393000

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/linux/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": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "=SoccerTwos training", "initialize_from": null, "load_model": false, "resume": false, "force": true, "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/linux/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: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: =SoccerTwos training
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: true
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,537 @@
+Mono path[0] = '/Users/giovannidispoto/ml-agents/training-envs-executables/linux/SoccerTwos/SoccerTwos.app/Contents/Resources/Data/Managed'
+Mono config path = '/Users/giovannidispoto/ml-agents/training-envs-executables/linux/SoccerTwos/SoccerTwos.app/Contents/MonoBleedingEdge/etc'
+New input system (experimental) initialized
+Initialize engine version: 2021.3.17f1 (3e8111cac19d)
+[Subsystems] Discovering subsystems at path /Users/giovannidispoto/ml-agents/training-envs-executables/linux/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  0.084 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: 0.325959 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
+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
+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
+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

run_logs/timers.json

@@ -0,0 +1,361 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 3.2730460166931152,
+            "min": 3.2722370624542236,
+            "max": 3.295734167098999,
+            "count": 13
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 72373.59375,
+            "min": 19247.623046875,
+            "max": 105463.4765625,
+            "count": 13
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 830.0,
+            "min": 727.5,
+            "max": 999.0,
+            "count": 13
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19920.0,
+            "min": 16748.0,
+            "max": 26100.0,
+            "count": 13
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1204.286574055704,
+            "min": 1199.9602811060863,
+            "max": 1204.286574055704,
+            "count": 12
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 4817.146296222816,
+            "min": 2402.3965187876356,
+            "max": 9599.68224884869,
+            "count": 12
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 129820.0,
+            "min": 9066.0,
+            "max": 129820.0,
+            "count": 13
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 129820.0,
+            "min": 9066.0,
+            "max": 129820.0,
+            "count": 13
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.0008173122187145054,
+            "min": -0.00990950409322977,
+            "max": 0.0052213906310498714,
+            "count": 13
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -0.009807746857404709,
+            "min": -0.12882354855537415,
+            "max": 0.06265668570995331,
+            "count": 13
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.0019189155427739024,
+            "min": -0.00903354398906231,
+            "max": 0.005207187030464411,
+            "count": 13
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -0.02302698604762554,
+            "min": -0.11743606626987457,
+            "max": 0.06248624250292778,
+            "count": 13
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 13
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 13
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.061700006326039634,
+            "min": -0.3194153859065129,
+            "max": 0.20903334021568298,
+            "count": 13
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -0.7404000759124756,
+            "min": -4.152400016784668,
+            "max": 2.508400082588196,
+            "count": 13
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.061700006326039634,
+            "min": -0.3194153859065129,
+            "max": 0.20903334021568298,
+            "count": 13
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -0.7404000759124756,
+            "min": -4.152400016784668,
+            "max": 2.508400082588196,
+            "count": 13
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 13
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 13
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.012841316836420447,
+            "min": 0.012841316836420447,
+            "max": 0.017041035451984498,
+            "count": 6
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.012841316836420447,
+            "min": 0.012841316836420447,
+            "max": 0.017041035451984498,
+            "count": 6
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.0021382930882585544,
+            "min": 0.0016193612692101548,
+            "max": 0.003799449202294151,
+            "count": 6
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.0021382930882585544,
+            "min": 0.0016193612692101548,
+            "max": 0.003799449202294151,
+            "count": 6
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.0021427319734357297,
+            "min": 0.0016194361300828557,
+            "max": 0.003858683972309033,
+            "count": 6
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.0021427319734357297,
+            "min": 0.0016194361300828557,
+            "max": 0.003858683972309033,
+            "count": 6
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 6
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 6
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 6
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 6
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 6
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 6
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1689870004",
+        "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/giovannidispoto/miniforge3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env training-envs-executables/linux/SoccerTwos/SoccerTwos --run-id =SoccerTwos training --force",
+        "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": "1689870497"
+    },
+    "total": 493.635118291,
+    "count": 1,
+    "self": 0.005367124000088097,
+    "children": {
+        "run_training.setup": {
+            "total": 0.012915374999999951,
+            "count": 1,
+            "self": 0.012915374999999951
+        },
+        "TrainerController.start_learning": {
+            "total": 493.61683579199996,
+            "count": 1,
+            "self": 0.09755877800296275,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 3.325448333,
+                    "count": 1,
+                    "self": 3.325448333
+                },
+                "TrainerController.advance": {
+                    "total": 489.970734097997,
+                    "count": 8888,
+                    "self": 0.0966509849946533,
+                    "children": {
+                        "env_step": {
+                            "total": 396.18781395499997,
+                            "count": 8888,
+                            "self": 380.7007259920022,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 15.422013874997418,
+                                    "count": 8888,
+                                    "self": 0.5089644479970659,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 14.913049427000352,
+                                            "count": 17648,
+                                            "self": 14.913049427000352
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.06507408800034975,
+                                    "count": 8887,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 486.1569761020012,
+                                            "count": 8887,
+                                            "is_parallel": true,
+                                            "self": 122.89936898400254,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.0015613330000001646,
+                                                    "count": 2,
+                                                    "is_parallel": true,
+                                                    "self": 0.000280333000000077,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.0012810000000000876,
+                                                            "count": 8,
+                                                            "is_parallel": true,
+                                                            "self": 0.0012810000000000876
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 363.25604578499866,
+                                                    "count": 8887,
+                                                    "is_parallel": true,
+                                                    "self": 0.9835880289940064,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 5.796755179999298,
+                                                            "count": 8887,
+                                                            "is_parallel": true,
+                                                            "self": 5.796755179999298
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 345.07033209000235,
+                                                            "count": 8887,
+                                                            "is_parallel": true,
+                                                            "self": 345.07033209000235
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 11.405370486002987,
+                                                            "count": 17774,
+                                                            "is_parallel": true,
+                                                            "self": 1.5637338320070846,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 9.841636653995902,
+                                                                    "count": 71096,
+                                                                    "is_parallel": true,
+                                                                    "self": 9.841636653995902
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 93.68626915800243,
+                            "count": 8887,
+                            "self": 0.7808035860016105,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 13.667919948000808,
+                                    "count": 8887,
+                                    "self": 13.667919948000808
+                                },
+                                "_update_policy": {
+                                    "total": 79.237545624,
+                                    "count": 6,
+                                    "self": 10.890855251999994,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 68.34669037200001,
+                                            "count": 180,
+                                            "self": 68.34669037200001
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 2.7499999987412593e-05,
+                    "count": 1,
+                    "self": 2.7499999987412593e-05
+                },
+                "TrainerController._save_models": {
+                    "total": 0.22306708299998945,
+                    "count": 1,
+                    "self": 0.0021550000000161162,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.22091208299997334,
+                            "count": 1,
+                            "self": 0.22091208299997334
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,30 @@
+{
+    "SoccerTwos": {
+        "elo": 1204.896264587993,
+        "checkpoints": [
+            {
+                "steps": 133820,
+                "file_path": "results/=SoccerTwos training/SoccerTwos/SoccerTwos-133820.onnx",
+                "reward": 0.0,
+                "creation_time": 1689870497.8246841,
+                "auxillary_file_paths": [
+                    "results/=SoccerTwos training/SoccerTwos/SoccerTwos-133820.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 133820,
+            "file_path": "results/=SoccerTwos training/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1689870497.8246841,
+            "auxillary_file_paths": [
+                "results/=SoccerTwos training/SoccerTwos/SoccerTwos-133820.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0"
+    }
+}