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: BabaYaga048/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 sha256:21c5d033dcaae7c9893cf98c436b54c44c22820acb77dae550dfba9bb3f537cb
+size 1764633

SoccerTwos/SoccerTwos-10000106.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21c5d033dcaae7c9893cf98c436b54c44c22820acb77dae550dfba9bb3f537cb
+size 1764633

SoccerTwos/SoccerTwos-10000106.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0022c1fac95443f7bef6b9a84c5aebb204a1adcece478dab7af9fb643868a58c
+size 28421201

SoccerTwos/SoccerTwos-8699946.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29955350fc5d107a6f0cdd9b70d0f8e7ab16203b565412c27fd829f5c8be7412
+size 1764633

SoccerTwos/SoccerTwos-8699946.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9de425867397faca7fdc5815536a98315a862627370e1e29e2aa83cc2eb5e3b
+size 28421201

SoccerTwos/SoccerTwos-8999970.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7da6336094d4ff16a5fd2361a4c533872294a1a978b02e48757a66e14c53a56
+size 1764633

SoccerTwos/SoccerTwos-8999970.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99862298efa1bb0193eda5a395eb2d3386f108432e5ba2eefd7c102b88878138
+size 28421201

SoccerTwos/SoccerTwos-9499970.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f485c1639ad632bbf053825c284e3a65356c9aa105f1e08b217db9c46e5a2c2
+size 1764633

SoccerTwos/SoccerTwos-9499970.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e95222e00c935476497aef36db3cfda2a39f754e72dd061d81f06b62e752ff3
+size 28421201

SoccerTwos/SoccerTwos-9999986.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21c5d033dcaae7c9893cf98c436b54c44c22820acb77dae550dfba9bb3f537cb
+size 1764633

SoccerTwos/SoccerTwos-9999986.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0b67da903a27b95d19b3c476d5c0fbf157abae38d2eafd94bc1a464ef9588ce
+size 28421201

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0022c1fac95443f7bef6b9a84c5aebb204a1adcece478dab7af9fb643868a58c
+size 28421201

SoccerTwos/events.out.tfevents.1692015946.SDS-555.local.64483.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:366b788035c640263cf67a280b25230d9c9a663facdd7a2c34c11314b59d703d
+size 5781955

SoccerTwos/events.out.tfevents.1692125296.SDS-555.local.73599.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db66eb1d49dc7196ade33bf64fe32038c2bb1a742246a053b36593b573092d57
+size 2303249

SoccerTwos/events.out.tfevents.1692207378.SDS-555.local.78631.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95e88f57de912cbf8aa0fcd6da819da3205b7619390be2a8736bbc9c2faede7d
+size 1347449

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": 10000000, "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: 10000000
+    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 +1,287 @@
+Mono path[0] = '/Users/soumojitbhattacharya/PycharmProjects/rl/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/Resources/Data/Managed'
+Mono config path = '/Users/soumojitbhattacharya/PycharmProjects/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/soumojitbhattacharya/PycharmProjects/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  0.196 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: 1.057500 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Setting up 4 worker threads for Enlighten.
+Memory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [8.0 KB-16.0 KB]: 24470 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 159 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 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]: 24471 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]: 24471 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]: 24470 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]: 24471 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]: 24471 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]: 24470 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]: 24471 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]: 24470 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": 1.5422695875167847,
+            "min": 1.358902931213379,
+            "max": 1.6392451524734497,
+            "count": 131
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 30203.806640625,
+            "min": 869.6978759765625,
+            "max": 35354.890625,
+            "count": 131
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 61.8875,
+            "min": 14.0,
+            "max": 72.31884057971014,
+            "count": 131
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19804.0,
+            "min": 112.0,
+            "max": 20420.0,
+            "count": 131
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1555.0830582808662,
+            "min": 1503.1061852957882,
+            "max": 1569.937910488838,
+            "count": 131
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 248813.2893249386,
+            "min": 6140.598878565317,
+            "max": 341490.80077715684,
+            "count": 131
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 9999986.0,
+            "min": 8699987.0,
+            "max": 9999986.0,
+            "count": 131
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 9999986.0,
+            "min": 8699987.0,
+            "max": 9999986.0,
+            "count": 131
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.039965007454156876,
+            "min": -0.07955111563205719,
+            "max": 0.07412034273147583,
+            "count": 131
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -6.354435920715332,
+            "min": -15.674731254577637,
+            "max": 12.600458145141602,
+            "count": 131
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.04035235196352005,
+            "min": -0.08584316074848175,
+            "max": 0.08051864057779312,
+            "count": 131
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -6.4160237312316895,
+            "min": -14.986276626586914,
+            "max": 13.688169479370117,
+            "count": 131
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 131
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 131
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.03440125670822911,
+            "min": -0.2702774581192546,
+            "max": 0.3316309686630003,
+            "count": 131
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -5.469799816608429,
+            "min": -55.96039962768555,
+            "max": 51.402800142765045,
+            "count": 131
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.03440125670822911,
+            "min": -0.2702774581192546,
+            "max": 0.3316309686630003,
+            "count": 131
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -5.469799816608429,
+            "min": -55.96039962768555,
+            "max": 51.402800142765045,
+            "count": 131
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 131
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 131
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.015145652223751919,
+            "min": 0.011791978035277376,
+            "max": 0.023321755667954372,
+            "count": 63
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.015145652223751919,
+            "min": 0.011791978035277376,
+            "max": 0.023321755667954372,
+            "count": 63
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.10312746713558833,
+            "min": 0.09516235515475273,
+            "max": 0.11794356231888135,
+            "count": 63
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.10312746713558833,
+            "min": 0.09516235515475273,
+            "max": 0.11794356231888135,
+            "count": 63
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.10443195899327597,
+            "min": 0.09606056759754816,
+            "max": 0.11946648806333542,
+            "count": 63
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.10443195899327597,
+            "min": 0.09606056759754816,
+            "max": 0.11946648806333542,
+            "count": 63
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 63
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 63
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 63
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 63
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 63
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 63
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1692207371",
+        "python_version": "3.9.17 (main, Jul  5 2023, 16:17:03) \n[Clang 14.0.6 ]",
+        "command_line_arguments": "/opt/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics --resume",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.11.0",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1692213584"
+    },
+    "total": 5904.371516334,
+    "count": 1,
+    "self": 2.3665285830002176,
+    "children": {
+        "run_training.setup": {
+            "total": 0.03477250000000254,
+            "count": 1,
+            "self": 0.03477250000000254
+        },
+        "TrainerController.start_learning": {
+            "total": 5901.970215251,
+            "count": 1,
+            "self": 1.335926395909155,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 6.9797415419994415,
+                    "count": 8,
+                    "self": 6.9797415419994415
+                },
+                "TrainerController.advance": {
+                    "total": 5893.388342604091,
+                    "count": 90501,
+                    "self": 1.1450277041085428,
+                    "children": {
+                        "env_step": {
+                            "total": 1214.93956218408,
+                            "count": 90501,
+                            "self": 980.8131489869226,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 233.3234402870467,
+                                    "count": 90501,
+                                    "self": 5.983297622016522,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 227.34014266503019,
+                                            "count": 163138,
+                                            "self": 227.34014266503019
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.802972910110654,
+                                    "count": 90501,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 5892.433743614063,
+                                            "count": 90501,
+                                            "is_parallel": true,
+                                            "self": 5054.01503899014,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.012321166999555544,
+                                                    "count": 16,
+                                                    "is_parallel": true,
+                                                    "self": 0.00219025000286166,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.010130916996693884,
+                                                            "count": 64,
+                                                            "is_parallel": true,
+                                                            "self": 0.010130916996693884
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 838.4063834569233,
+                                                    "count": 90501,
+                                                    "is_parallel": true,
+                                                    "self": 45.301781421703595,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 26.50081490400531,
+                                                            "count": 90501,
+                                                            "is_parallel": true,
+                                                            "self": 26.50081490400531
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 647.0776638040975,
+                                                            "count": 90501,
+                                                            "is_parallel": true,
+                                                            "self": 647.0776638040975
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 119.52612332711689,
+                                                            "count": 181002,
+                                                            "is_parallel": true,
+                                                            "self": 20.076650796359928,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 99.44947253075696,
+                                                                    "count": 724008,
+                                                                    "is_parallel": true,
+                                                                    "self": 99.44947253075696
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 4677.303752715903,
+                            "count": 90501,
+                            "self": 11.050956303944986,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 590.7645311589569,
+                                    "count": 90501,
+                                    "self": 589.4128263679576,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 1.3517047909992925,
+                                            "count": 3,
+                                            "self": 1.3517047909992925
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 4075.4882652530014,
+                                    "count": 63,
+                                    "self": 165.5546123100121,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 3909.9336529429893,
+                                            "count": 1890,
+                                            "self": 3909.9336529429893
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 5.840001904289238e-07,
+                    "count": 1,
+                    "self": 5.840001904289238e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.26620412499960366,
+                    "count": 1,
+                    "self": 0.01405583299947466,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.252148292000129,
+                            "count": 1,
+                            "self": 0.252148292000129
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 8699946,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8699946.onnx",
+                "reward": null,
+                "creation_time": 1692193732.5399811,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8699946.pt"
+                ]
+            },
+            {
+                "steps": 8999970,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8999970.onnx",
+                "reward": 0.0,
+                "creation_time": 1692208691.274013,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8999970.pt"
+                ]
+            },
+            {
+                "steps": 9499970,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-9499970.onnx",
+                "reward": 0.0,
+                "creation_time": 1692210922.778374,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-9499970.pt"
+                ]
+            },
+            {
+                "steps": 9999986,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-9999986.onnx",
+                "reward": 0.0,
+                "creation_time": 1692213581.416762,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-9999986.pt"
+                ]
+            },
+            {
+                "steps": 10000106,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-10000106.onnx",
+                "reward": 0.0,
+                "creation_time": 1692213581.722642,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-10000106.pt"
+                ]
+            }
+        ],
+        "elo": 1553.7218983912148,
+        "final_checkpoint": {
+            "steps": 10000106,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1692213581.722642,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-10000106.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0"
+    }
+}