First Push-11M add 1.2M to v.2

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: vagi/poca-SoccerTwos-v2.1
+  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 sha256:89468611093b2b2b4e43379c73f0bb426207614aa3346f83957241596a10df92
+size 1768747

SoccerTwos/SoccerTwos-10000228.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92c34f46b767939a5638d758273becc5a52b4e3ee446e57c1faff014be11376d
+size 1768747

SoccerTwos/SoccerTwos-10000228.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:344a42e62af384387e7d88679331491cc13872fc34e4fb47bb63acc3d7e37aff
+size 28430482

SoccerTwos/SoccerTwos-10499763.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:267fbf0f8ba9e094e513c566e34a60fd8d0884d786b36df1a868088d5e0b4225
+size 1768747

SoccerTwos/SoccerTwos-10499763.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55a25d416d33f9b36dc94a14ce0d46bcae4e1ae92ad1e30cad0b06b2ee13a3a0
+size 28430482

SoccerTwos/SoccerTwos-10999926.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c569de4a922a23ead2df538b47bec21012d31fa5e056bda076a78805e16b302d
+size 1768747

SoccerTwos/SoccerTwos-10999926.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d054628a32819dbe39d4d55bf0fa1f2f1e3234b258a89473519d0cbe13c708d6
+size 28430482

SoccerTwos/SoccerTwos-11232766.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89468611093b2b2b4e43379c73f0bb426207614aa3346f83957241596a10df92
+size 1768747

SoccerTwos/SoccerTwos-11232766.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a72ad19e4443cd9be343a41e0dd295a6f4b909b9e598af7e94dd5382ab2d58ab
+size 28430482

SoccerTwos/SoccerTwos-9999874.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92c34f46b767939a5638d758273becc5a52b4e3ee446e57c1faff014be11376d
+size 1768747

SoccerTwos/SoccerTwos-9999874.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92e053401f59cfc90085336a54b563f80f73884d64a196525211f0537c0d77b7
+size 28430358

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb03c8448546bf43c20d5258d9393d814104298096fd0d1e88ac81692b231cfc
+size 28429366

SoccerTwos/events.out.tfevents.1733319990.MacBook-Pro---Mango.local.8008.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cd618c08b0321d2307b99c0daa11780cdbea839834dfca4b5e71df260301dbf
+size 1312461

SoccerTwos/events.out.tfevents.1733339739.MacBook-Pro---Mango.local.9808.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dee570564fab33d1f9bb759ce3212eb16d9f4523c5f335249668678bf4efec3f
+size 92573

SoccerTwos/events.out.tfevents.1733386158.MacBook-Pro---Mango.local.10750.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd2a9edd6868e48363779bcb0117b278310d9d381a5a66efbcffd6d7a172d34f
+size 886343

SoccerTwos/events.out.tfevents.1733415062.MacBook-Pro---Mango.local.11803.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51e92d4826a07177e4e1486186eecae24d40bd82b01140d51fd2ab198e1baa53
+size 1354517

SoccerTwos/events.out.tfevents.1733480468.MacBook-Pro---Mango.local.13748.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e945dccea247d12c8f5073656e92256d0ba30f45a11ffd78b4cb00d9830ae71b
+size 672649

SoccerTwos/events.out.tfevents.1733517597.MacBook-Pro---Mango.local.16536.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f664a1e08cb926f4e997c4ef60a80574bc211f9fab9ae77b81b05bf1b220831f
+size 530417

SoccerTwos/events.out.tfevents.1733560364.MacBook-Pro---Mango.local.17653.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dee8deaf57a182c97871e11ee4406f41b60fbe4a21c96af678537287fc6ed855
+size 225041

SoccerTwos/events.out.tfevents.1733596911.MacBook-Pro---Mango.local.19769.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a197d19243221f173147bd15a512e40b1b793c201e6112a210a457a8c017ed9
+size 621753

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 102400, "learning_rate": 0.0005, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 5, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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": 0.98, "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": 13000000, "time_horizon": 1512, "summary_freq": 20000, "threaded": false, "self_play": {"save_steps": 75000, "team_change": 300000, "swap_steps": 30000, "window": 17, "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, "timeout_wait": 60, "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, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos-v2", "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 +1,84 @@
+default_settings: null
+behaviors:
+  SoccerTwos:
+    trainer_type: poca
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 102400
+      learning_rate: 0.0005
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 5
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    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: 0.98
+        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: 13000000
+    time_horizon: 1512
+    summary_freq: 20000
+    threaded: false
+    self_play:
+      save_steps: 75000
+      team_change: 300000
+      swap_steps: 30000
+      window: 17
+      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
+  timeout_wait: 60
+  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
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: SoccerTwos-v2
+  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 +1,308 @@
+Mono path[0] = '/Users/mango/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/Resources/Data/Managed'
+Mono config path = '/Users/mango/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/mango/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  0.197 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: 2.510794 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+GRPC Exception: Status(StatusCode=Unknown, Detail="Exception calling application: [Errno 32] Broken pipe"). Disconnecting from trainer.
+Setting up 6 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]: 23157 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 128 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 78.8 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 6
+      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 11
+      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_Job.Worker 9]
+      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 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 8]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 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 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 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 0.7 KB
+      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_Job.Worker 10]
+      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 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 3
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 23158 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]: 23158 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]: 23157 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]: 23158 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]: 23158 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]: 23157 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 3.0 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]: 23158 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]: 23157 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": 1.8996624946594238,
+            "min": 1.886587142944336,
+            "max": 2.0112533569335938,
+            "count": 61
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 77019.9140625,
+            "min": 74277.203125,
+            "max": 83170.4296875,
+            "count": 61
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 44.34703196347032,
+            "min": 39.54251012145749,
+            "max": 52.645161290322584,
+            "count": 61
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 38848.0,
+            "min": 38620.0,
+            "max": 39760.0,
+            "count": 61
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1595.5836355998229,
+            "min": 1581.8719700331785,
+            "max": 1629.204667611585,
+            "count": 61
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 698865.6323927224,
+            "min": 589617.790705327,
+            "max": 789016.2937724582,
+            "count": 61
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 11219996.0,
+            "min": 10019919.0,
+            "max": 11219996.0,
+            "count": 61
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 11219996.0,
+            "min": 10019919.0,
+            "max": 11219996.0,
+            "count": 61
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": 0.00622489582747221,
+            "min": -0.05283130705356598,
+            "max": 0.04666583240032196,
+            "count": 61
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": 2.726504325866699,
+            "min": -24.091075897216797,
+            "max": 20.672964096069336,
+            "count": 61
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.0041276742704212666,
+            "min": -0.05068834871053696,
+            "max": 0.04481092467904091,
+            "count": 61
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 1.8079214096069336,
+            "min": -23.113887786865234,
+            "max": 19.851240158081055,
+            "count": 61
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 61
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 61
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.03666027441416701,
+            "min": -0.1891298249625323,
+            "max": 0.12896794740018133,
+            "count": 61
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -16.05720019340515,
+            "min": -86.24320018291473,
+            "max": 57.132800698280334,
+            "count": 61
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.03666027441416701,
+            "min": -0.1891298249625323,
+            "max": 0.12896794740018133,
+            "count": 61
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -16.05720019340515,
+            "min": -86.24320018291473,
+            "max": 57.132800698280334,
+            "count": 61
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 61
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 61
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.018658186582964843,
+            "min": 0.017024516874807886,
+            "max": 0.01911724130413495,
+            "count": 11
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.018658186582964843,
+            "min": 0.017024516874807886,
+            "max": 0.01911724130413495,
+            "count": 11
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.08370085209608077,
+            "min": 0.0768383824378252,
+            "max": 0.08370085209608077,
+            "count": 11
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.08370085209608077,
+            "min": 0.0768383824378252,
+            "max": 0.08370085209608077,
+            "count": 11
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.0886788744032383,
+            "min": 0.08260714703798294,
+            "max": 0.08937660717964173,
+            "count": 11
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.0886788744032383,
+            "min": 0.08260714703798294,
+            "max": 0.08937660717964173,
+            "count": 11
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 7.202685482541537e-05,
+            "min": 7.202685482541537e-05,
+            "max": 0.00011143723155872304,
+            "count": 11
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 7.202685482541537e-05,
+            "min": 7.202685482541537e-05,
+            "max": 0.00011143723155872304,
+            "count": 11
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.11440535384615381,
+            "min": 0.11440535384615381,
+            "max": 0.12228743076923076,
+            "count": 11
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.11440535384615381,
+            "min": 0.11440535384615381,
+            "max": 0.12228743076923076,
+            "count": 11
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.0007288271569230769,
+            "min": 0.0007288271569230769,
+            "max": 0.0011221427953846152,
+            "count": 11
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.0007288271569230769,
+            "min": 0.0007288271569230769,
+            "max": 0.0011221427953846152,
+            "count": 11
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1733596907",
+        "python_version": "3.10.12 (main, Jul  5 2023, 15:34:07) [Clang 14.0.6 ]",
+        "command_line_arguments": "/Users/mango/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos-v2 --no-graphics --resume",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.2.2",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1733606074"
+    },
+    "total": 9167.079563773994,
+    "count": 1,
+    "self": 1.219165108006564,
+    "children": {
+        "run_training.setup": {
+            "total": 0.042149560002144426,
+            "count": 1,
+            "self": 0.042149560002144426
+        },
+        "TrainerController.start_learning": {
+            "total": 9165.818249105985,
+            "count": 1,
+            "self": 1.8252556156221544,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 5.141387626994401,
+                    "count": 6,
+                    "self": 5.141387626994401
+                },
+                "TrainerController.advance": {
+                    "total": 9158.619714393368,
+                    "count": 87899,
+                    "self": 1.6758576652646298,
+                    "children": {
+                        "env_step": {
+                            "total": 6379.429527955668,
+                            "count": 87899,
+                            "self": 6162.35989666915,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 215.99093429616187,
+                                    "count": 87899,
+                                    "self": 8.583292969182367,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 207.4076413269795,
+                                            "count": 154384,
+                                            "self": 207.4076413269795
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 1.0786969903565478,
+                                    "count": 87898,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 9158.916076981273,
+                                            "count": 87898,
+                                            "is_parallel": true,
+                                            "self": 3180.6766884052486,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.01726108498405665,
+                                                    "count": 12,
+                                                    "is_parallel": true,
+                                                    "self": 0.002374373027123511,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.01488671195693314,
+                                                            "count": 48,
+                                                            "is_parallel": true,
+                                                            "self": 0.01488671195693314
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 5978.222127491041,
+                                                    "count": 87898,
+                                                    "is_parallel": true,
+                                                    "self": 18.891270804422675,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 120.4005277333199,
+                                                            "count": 87898,
+                                                            "is_parallel": true,
+                                                            "self": 120.4005277333199
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 5619.16723036037,
+                                                            "count": 87898,
+                                                            "is_parallel": true,
+                                                            "self": 5619.16723036037
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 219.76309859292815,
+                                                            "count": 175796,
+                                                            "is_parallel": true,
+                                                            "self": 29.732495062737144,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 190.030603530191,
+                                                                    "count": 703184,
+                                                                    "is_parallel": true,
+                                                                    "self": 190.030603530191
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 2777.514328772435,
+                            "count": 87898,
+                            "self": 11.803366322768852,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 275.05257099067967,
+                                    "count": 87898,
+                                    "self": 274.4803247986856,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.5722461919940542,
+                                            "count": 2,
+                                            "self": 0.5722461919940542
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 2490.6583914589864,
+                                    "count": 12,
+                                    "self": 267.51975328261324,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 2223.138638176373,
+                                            "count": 3000,
+                                            "self": 2223.138638176373
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 9.280047379434109e-07,
+                    "count": 1,
+                    "self": 9.280047379434109e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.23189054199610837,
+                    "count": 1,
+                    "self": 0.002295552985742688,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.22959498901036568,
+                            "count": 1,
+                            "self": 0.22959498901036568
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 9999874,
+                "file_path": "results/SoccerTwos-v2/SoccerTwos/SoccerTwos-9999874.onnx",
+                "reward": 0.0,
+                "creation_time": 1733563314.68068,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos-v2/SoccerTwos/SoccerTwos-9999874.pt"
+                ]
+            },
+            {
+                "steps": 10000228,
+                "file_path": "results/SoccerTwos-v2/SoccerTwos/SoccerTwos-10000228.onnx",
+                "reward": 0.0,
+                "creation_time": 1733563314.918973,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos-v2/SoccerTwos/SoccerTwos-10000228.pt"
+                ]
+            },
+            {
+                "steps": 10499763,
+                "file_path": "results/SoccerTwos-v2/SoccerTwos/SoccerTwos-10499763.onnx",
+                "reward": 0.0,
+                "creation_time": 1733600544.720098,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos-v2/SoccerTwos/SoccerTwos-10499763.pt"
+                ]
+            },
+            {
+                "steps": 10999926,
+                "file_path": "results/SoccerTwos-v2/SoccerTwos/SoccerTwos-10999926.onnx",
+                "reward": 0.0,
+                "creation_time": 1733604246.0211751,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos-v2/SoccerTwos/SoccerTwos-10999926.pt"
+                ]
+            },
+            {
+                "steps": 11232766,
+                "file_path": "results/SoccerTwos-v2/SoccerTwos/SoccerTwos-11232766.onnx",
+                "reward": 0.0,
+                "creation_time": 1733606073.517463,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos-v2/SoccerTwos/SoccerTwos-11232766.pt"
+                ]
+            }
+        ],
+        "elo": 1595.5836355998233,
+        "final_checkpoint": {
+            "steps": 11232766,
+            "file_path": "results/SoccerTwos-v2/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1733606073.517463,
+            "auxillary_file_paths": [
+                "results/SoccerTwos-v2/SoccerTwos/SoccerTwos-11232766.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.2.2"
+    }
+}