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: i-pj/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 sha256:1bc9e6865da08a1f85ca054ac0e3321ea6319a963634f2db4a42c1e52c22cfbe
+size 1768747

SoccerTwos/SoccerTwos-10170124.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bc9e6865da08a1f85ca054ac0e3321ea6319a963634f2db4a42c1e52c22cfbe
+size 1768747

SoccerTwos/SoccerTwos-10170124.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:531eff09111d76df93dbbf3e478a92b017fa4afcf9aedac9126483463808707d
+size 28430482

SoccerTwos/SoccerTwos-7999934.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0df83b7fa2f10ead9e7dfe8ecc744ea162108e2114f775ccabae893cb24160a4
+size 1768747

SoccerTwos/SoccerTwos-7999934.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:500ebd340f5519637bc52b6410e4dc9e574162c1e7c2c75aae0e06436881753c
+size 28430358

SoccerTwos/SoccerTwos-8499999.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eee67161f503b99c073f9d51853c6e5b15226260eb1b6d91b7344c3f804880e
+size 1768747

SoccerTwos/SoccerTwos-8499999.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a70f56fa7556aaef5e829561886443d1d1631af4ecc8f3e733f463bc96ffab40
+size 28430358

SoccerTwos/SoccerTwos-8999984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e8af319c4cd5558ea79ab7e52691bd84d30403c35f7a2f8d9b8f350d916fa41
+size 1768747

SoccerTwos/SoccerTwos-8999984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea2ff37ab7445b3fdfd76e4e79a4acc3de9f2f5943e7881fa6858c14996a7ac9
+size 28430358

SoccerTwos/SoccerTwos-9499769.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:900adbfc26925bd9ce4e9c4286b3ef6e2213713f0993a03f8d205db2dd09cd55
+size 1768747

SoccerTwos/SoccerTwos-9499769.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dfed12f206973f1b5c074fc00d1e375d898acaa8c07056df26deb8cff36b313
+size 28430358

SoccerTwos/SoccerTwos-9999926.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad4003ef23ef69c34784e7c9847f816b8793d9f9086df8b84d067e7309155af
+size 1768747

SoccerTwos/SoccerTwos-9999926.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bc2deacea02cda5d355d619f81abdc01c1a3d4d0f7501f69bb8241cea99bfc1
+size 28430358

SoccerTwos/SoccerTwos-9999982.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad4003ef23ef69c34784e7c9847f816b8793d9f9086df8b84d067e7309155af
+size 1768747

SoccerTwos/SoccerTwos-9999982.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f46104132cc581b81ff79487a5549c7e177f9d4a527f19d7d8f0b56ddf937364
+size 28430358

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e28f86474877acd64841c9618eb24c175d48f8b0a3c486fd24cd275c0751ec6d
+size 28429366

SoccerTwos/events.out.tfevents.1714154911.Parths-MacBook-Pro-3.local.79483.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0d9d2d77f9acfa6043f4837f16aa3b76b65b294c1c81c5d8a0e343e59c3b4cb
+size 9539810

SoccerTwos/events.out.tfevents.1714188444.Parths-MacBook-Pro-3.local.49112.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4cadd9608b5ee4e97510a1d3251d51af3a4bb20132cb63c28eb5ca4319326c5
+size 185989

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": 10170000, "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, "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", "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: 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: 10170000
+    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
+  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
+  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/parth/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/Resources/Data/Managed'
+Mono config path = '/Users/parth/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/parth/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  0.084 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: 1.149125 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Thread 0x170eb7000 may have been prematurely finalized
+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]: 3201 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 0.7 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 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 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_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]: 3202 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]: 3202 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.3 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]: 3201 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]: 3202 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]: 3202 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]: 3201 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]: 3202 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]: 3201 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": 1.679749846458435,
+            "min": 1.5837690830230713,
+            "max": 1.6931036710739136,
+            "count": 18
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 33379.98828125,
+            "min": 1165.654052734375,
+            "max": 35658.38671875,
+            "count": 18
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 62.64102564102564,
+            "min": 18.5,
+            "max": 87.15789473684211,
+            "count": 18
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19544.0,
+            "min": 148.0,
+            "max": 20304.0,
+            "count": 18
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1222.809791901454,
+            "min": 1193.0768502042945,
+            "max": 1226.4892024962849,
+            "count": 18
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 190758.32753662684,
+            "min": 4800.0,
+            "max": 201144.22920939073,
+            "count": 18
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 10169935.0,
+            "min": 9999982.0,
+            "max": 10169935.0,
+            "count": 18
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 10169935.0,
+            "min": 9999982.0,
+            "max": 10169935.0,
+            "count": 18
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.006176153663545847,
+            "min": -0.024318289011716843,
+            "max": 0.19033126533031464,
+            "count": 18
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -0.9634799957275391,
+            "min": -3.6477432250976562,
+            "max": 15.603649139404297,
+            "count": 18
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.0054854401387274265,
+            "min": -0.023617848753929138,
+            "max": 0.19180536270141602,
+            "count": 18
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -0.8557286262512207,
+            "min": -3.542677402496338,
+            "max": 15.997982025146484,
+            "count": 18
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 18
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 18
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.1732794864055438,
+            "min": -0.1732794864055438,
+            "max": 0.3216000000635783,
+            "count": 18
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -27.03159987926483,
+            "min": -27.03159987926483,
+            "max": 46.63159966468811,
+            "count": 18
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.1732794864055438,
+            "min": -0.1732794864055438,
+            "max": 0.3216000000635783,
+            "count": 18
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -27.03159987926483,
+            "min": -27.03159987926483,
+            "max": 46.63159966468811,
+            "count": 18
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 18
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 18
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.015739139712726075,
+            "min": 0.014609941675735172,
+            "max": 0.01964028791990131,
+            "count": 8
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.015739139712726075,
+            "min": 0.014609941675735172,
+            "max": 0.01964028791990131,
+            "count": 8
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.0893124724427859,
+            "min": 0.08485158532857895,
+            "max": 0.09563147947192192,
+            "count": 8
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.0893124724427859,
+            "min": 0.08485158532857895,
+            "max": 0.09563147947192192,
+            "count": 8
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.09080011248588563,
+            "min": 0.08616696794827779,
+            "max": 0.09690051277478536,
+            "count": 8
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.09080011248588563,
+            "min": 0.08616696794827779,
+            "max": 0.09690051277478536,
+            "count": 8
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 8
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 8
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 8
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 8
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 8
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 8
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1714188442",
+        "python_version": "3.10.12 (main, Jul  5 2023, 15:02:25) [Clang 14.0.6 ]",
+        "command_line_arguments": "/Users/parth/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics --resume",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.3.0",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1714189152"
+    },
+    "total": 710.7810192499892,
+    "count": 1,
+    "self": 0.23493162498925813,
+    "children": {
+        "run_training.setup": {
+            "total": 0.028353750007227063,
+            "count": 1,
+            "self": 0.028353750007227063
+        },
+        "TrainerController.start_learning": {
+            "total": 710.5177338749927,
+            "count": 1,
+            "self": 0.1342643857933581,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.631008541007759,
+                    "count": 2,
+                    "self": 2.631008541007759
+                },
+                "TrainerController.advance": {
+                    "total": 707.6277636972081,
+                    "count": 11636,
+                    "self": 0.12268581980606541,
+                    "children": {
+                        "env_step": {
+                            "total": 568.1032658139302,
+                            "count": 11636,
+                            "self": 548.0383035824925,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 19.98557951292605,
+                                    "count": 11636,
+                                    "self": 0.7190609581302851,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 19.266518554795766,
+                                            "count": 21346,
+                                            "self": 19.266518554795766
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.07938271851162426,
+                                    "count": 11636,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 708.1492451805389,
+                                            "count": 11636,
+                                            "is_parallel": true,
+                                            "self": 177.74469017470255,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.0037761230196338147,
+                                                    "count": 4,
+                                                    "is_parallel": true,
+                                                    "self": 0.0005192049720790237,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.003256918047554791,
+                                                            "count": 16,
+                                                            "is_parallel": true,
+                                                            "self": 0.003256918047554791
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 530.4007788828167,
+                                                    "count": 11636,
+                                                    "is_parallel": true,
+                                                    "self": 1.4402798907249235,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 9.246110053150915,
+                                                            "count": 11636,
+                                                            "is_parallel": true,
+                                                            "self": 9.246110053150915
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 500.89330227387836,
+                                                            "count": 11636,
+                                                            "is_parallel": true,
+                                                            "self": 500.89330227387836
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 18.821086665062467,
+                                                            "count": 23272,
+                                                            "is_parallel": true,
+                                                            "self": 2.077526547946036,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 16.74356011711643,
+                                                                    "count": 93088,
+                                                                    "is_parallel": true,
+                                                                    "self": 16.74356011711643
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 139.40181206347188,
+                            "count": 11636,
+                            "self": 1.0675276794936508,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 29.373940135963494,
+                                    "count": 11636,
+                                    "self": 29.23191492795013,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.14202520801336505,
+                                            "count": 1,
+                                            "self": 0.14202520801336505
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 108.96034424801474,
+                                    "count": 8,
+                                    "self": 12.666946159064537,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 96.2933980889502,
+                                            "count": 240,
+                                            "self": 96.2933980889502
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 4.5899651013314724e-07,
+                    "count": 1,
+                    "self": 4.5899651013314724e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.12469679198693484,
+                    "count": 1,
+                    "self": 0.0009215000027325004,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.12377529198420234,
+                            "count": 1,
+                            "self": 0.12377529198420234
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,39 @@
+{
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.3.0"
+    },
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 9999982,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-9999982.onnx",
+                "reward": 0.0,
+                "creation_time": 1714188446.15301,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-9999982.pt"
+                ]
+            },
+            {
+                "steps": 10170124,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-10170124.onnx",
+                "reward": 0.0,
+                "creation_time": 1714189152.593143,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-10170124.pt"
+                ]
+            }
+        ],
+        "elo": 1218.3896753698098,
+        "final_checkpoint": {
+            "steps": 10170124,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1714189152.593143,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-10170124.pt"
+            ]
+        }
+    }
+}