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: SpyrosMitsis/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:fa197650f1d2e3fb265cc26a253195ad5bc601f99efa523de691fc94347035f3
+size 1768747

SoccerTwos/SoccerTwos-4999964.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06e46a79c0a1e7deb858216ddecbe9e636322850f55d37c1d448b83e4b400989
+size 1768747

SoccerTwos/SoccerTwos-4999964.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c9e7cba38969537089b52ac29b32e102888eea9c90e7ae3e2182980c7c174be
+size 28432022

SoccerTwos/SoccerTwos-5499978.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d96269a877640bfc92f647f7bac936abc8df7679b23cf3f33a46b717a055248
+size 1768747

SoccerTwos/SoccerTwos-5499978.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1d4397206c6f7410b8490decd9352f7dc020d5aafd08f2ae998afa7e3f17c72
+size 28432022

SoccerTwos/SoccerTwos-5999978.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff2821fffef39a7681bcbde5d3d4531948b5e47ca941febd9026ee553837e3e0
+size 1768747

SoccerTwos/SoccerTwos-5999978.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a9afea7abaf3b36d8ba7c0b85c8254815dbcbd20fe83f47277fddb1c3fdf4c8
+size 28432022

SoccerTwos/SoccerTwos-6499982.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa197650f1d2e3fb265cc26a253195ad5bc601f99efa523de691fc94347035f3
+size 1768747

SoccerTwos/SoccerTwos-6499982.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e75df2c4c5cf5793c86695173a28978333b6146f2a27300c65129625e698377
+size 28432022

SoccerTwos/SoccerTwos-6502722.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa197650f1d2e3fb265cc26a253195ad5bc601f99efa523de691fc94347035f3
+size 1768747

SoccerTwos/SoccerTwos-6502722.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24d1655ba1995840822187620d42e4a117b90d1516badd65674716903d07c6a8
+size 28432022

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1812f232d3a8e82dcbf339229084a1f3348623a9eb1b82cbd6c01f50a1bdf584
+size 28431030

SoccerTwos/events.out.tfevents.1727099395.Spyros.72476.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a1ab2b6dc4600f5f712800c46a855c0f3416eb81bce105a9eaa10d945cec498
+size 6523656

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 50000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 70000, "team_change": 350000, "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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,83 @@
+default_settings: null
+behaviors:
+  SoccerTwos:
+    trainer_type: poca
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: constant
+      beta_schedule: constant
+      epsilon_schedule: constant
+    checkpoint_interval: 500000
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 2
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+    init_path: null
+    keep_checkpoints: 5
+    even_checkpoints: false
+    max_steps: 50000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 70000
+      team_change: 350000
+      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
+environment_parameters: null
+checkpoint_settings:
+  run_id: SoccerTwos
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: true
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,682 @@
+Mono path[0] = '/home/smitsis/deep_rl/unit7/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = '/home/smitsis/deep_rl/unit7/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+PlayerPrefs - Creating folder: /home/smitsis/.config/unity3d/Unity Technologies/SoccerTwos
+Unable to load player prefs
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /home/smitsis/deep_rl/unit7/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_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  0.131 seconds
+ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard (Specular setup)' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Standard (Specular setup) shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard (Specular setup)' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'Standard' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+UnloadTime: 0.702717 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+requesting resize 84 x 84
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+Setting up 10 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]: 122480 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_Job.Worker 18]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.7 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 300.0 KB
+      Peak Allocated Bytes 249.6 KB
+      Overflow Count 4
+    [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_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_Job.Worker 16]
+      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 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 17]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 14]
+      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_Job.Worker 13]
+      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 10
+      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 19
+      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_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_Job.Worker 15]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 11]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 12]
+      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 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]: 122481 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 4.8 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 122481 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.5 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]: 122480 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]: 122481 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]: 122481 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]: 122480 frames, [4.0 MB-8.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 2
+      Peak Allocated memory 4.5 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]: 122481 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]: 122480 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 +1,424 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 1.8774759769439697,
+            "min": 1.8230854272842407,
+            "max": 3.2957592010498047,
+            "count": 650
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 37369.28125,
+            "min": 31598.404296875,
+            "max": 125238.84375,
+            "count": 650
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 65.14473684210526,
+            "min": 45.39449541284404,
+            "max": 999.0,
+            "count": 650
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19804.0,
+            "min": 12808.0,
+            "max": 28468.0,
+            "count": 650
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1657.5226141061385,
+            "min": 1198.7535925691843,
+            "max": 1657.5226141061385,
+            "count": 644
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 251943.43734413304,
+            "min": 2403.7680185623153,
+            "max": 347966.3823908464,
+            "count": 644
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 6499982.0,
+            "min": 9250.0,
+            "max": 6499982.0,
+            "count": 650
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 6499982.0,
+            "min": 9250.0,
+            "max": 6499982.0,
+            "count": 650
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.03020160272717476,
+            "min": -0.1315937340259552,
+            "max": 0.31489238142967224,
+            "count": 650
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -4.560441970825195,
+            "min": -19.592727661132812,
+            "max": 42.04832458496094,
+            "count": 650
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.028834901750087738,
+            "min": -0.13370631635189056,
+            "max": 0.3127575218677521,
+            "count": 650
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -4.35407018661499,
+            "min": -19.63623809814453,
+            "max": 42.27655029296875,
+            "count": 650
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 650
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 650
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.08127682335329371,
+            "min": -0.5777799993753433,
+            "max": 0.5952825366504608,
+            "count": 650
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -12.272800326347351,
+            "min": -50.421999633312225,
+            "max": 86.74399983882904,
+            "count": 650
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.08127682335329371,
+            "min": -0.5777799993753433,
+            "max": 0.5952825366504608,
+            "count": 650
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -12.272800326347351,
+            "min": -50.421999633312225,
+            "max": 86.74399983882904,
+            "count": 650
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 650
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 650
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.015245077373522993,
+            "min": 0.010870925474834318,
+            "max": 0.024924556460852423,
+            "count": 313
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.015245077373522993,
+            "min": 0.010870925474834318,
+            "max": 0.024924556460852423,
+            "count": 313
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.09139621928334236,
+            "min": 0.00011678574228426441,
+            "max": 0.11551008224487305,
+            "count": 313
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.09139621928334236,
+            "min": 0.00011678574228426441,
+            "max": 0.11551008224487305,
+            "count": 313
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.09248334566752116,
+            "min": 0.00012518015209934675,
+            "max": 0.11676155601938566,
+            "count": 313
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.09248334566752116,
+            "min": 0.00012518015209934675,
+            "max": 0.11676155601938566,
+            "count": 313
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 313
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 313
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 313
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 313
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 313
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 313
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1727099394",
+        "python_version": "3.10.12 (main, Sep 23 2024, 16:48:48) [GCC 11.4.0]",
+        "command_line_arguments": "/home/smitsis/deep_rl/unit7/ml-agents/.venv/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics --force",
+        "mlagents_version": "1.0.0",
+        "mlagents_envs_version": "1.0.0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.4.1+cu121",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1727114671"
+    },
+    "total": 15277.358717189998,
+    "count": 1,
+    "self": 0.2107879139985016,
+    "children": {
+        "run_training.setup": {
+            "total": 0.014571755000361009,
+            "count": 1,
+            "self": 0.014571755000361009
+        },
+        "TrainerController.start_learning": {
+            "total": 15277.133357521,
+            "count": 1,
+            "self": 13.382955916942592,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 3.1114011030058464,
+                    "count": 19,
+                    "self": 3.1114011030058464
+                },
+                "TrainerController.advance": {
+                    "total": 15260.148709124049,
+                    "count": 442889,
+                    "self": 13.362418611493922,
+                    "children": {
+                        "env_step": {
+                            "total": 10468.270577584424,
+                            "count": 442889,
+                            "self": 5768.788711935371,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 4692.116632672116,
+                                    "count": 442889,
+                                    "self": 80.83054285169055,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 4611.286089820425,
+                                            "count": 816546,
+                                            "self": 4611.286089820425
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 7.365232976937477,
+                                    "count": 442889,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 15258.663917305925,
+                                            "count": 442889,
+                                            "is_parallel": true,
+                                            "self": 10963.82709216906,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0016971800014289329,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005622120061161695,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0011349679953127634,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0011349679953127634
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.021635789998981636,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0004916239977319492,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0006636550006078323,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0006636550006078323
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.01868441599981452,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.01868441599981452
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0017960950008273358,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004361360006441828,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.001359959000183153,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.001359959000183153
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 4294.809464913864,
+                                                    "count": 442888,
+                                                    "is_parallel": true,
+                                                    "self": 180.9360052807133,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 204.9597975631732,
+                                                            "count": 442888,
+                                                            "is_parallel": true,
+                                                            "self": 204.9597975631732
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 3274.868720286333,
+                                                            "count": 442888,
+                                                            "is_parallel": true,
+                                                            "self": 3274.868720286333
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 634.0449417836444,
+                                                            "count": 885776,
+                                                            "is_parallel": true,
+                                                            "self": 149.30680120312172,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 484.73814058052267,
+                                                                    "count": 3543104,
+                                                                    "is_parallel": true,
+                                                                    "self": 484.73814058052267
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.027360223000869155,
+                                                    "count": 36,
+                                                    "is_parallel": true,
+                                                    "self": 0.006583262016647495,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.02077696098422166,
+                                                            "count": 144,
+                                                            "is_parallel": true,
+                                                            "self": 0.02077696098422166
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 4778.515712928131,
+                            "count": 442889,
+                            "self": 91.62737726339401,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 1949.8084437717662,
+                                    "count": 442889,
+                                    "self": 1944.7308315997652,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 5.077612172000954,
+                                            "count": 13,
+                                            "self": 5.077612172000954
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 2737.0798918929704,
+                                    "count": 313,
+                                    "self": 1955.5204607951237,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 781.5594310978468,
+                                            "count": 9390,
+                                            "self": 781.5594310978468
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.3899989426136017e-06,
+                    "count": 1,
+                    "self": 1.3899989426136017e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.4902899870030524,
+                    "count": 1,
+                    "self": 0.015460426002391614,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.47482956100066076,
+                            "count": 1,
+                            "self": 0.47482956100066076
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 4999964,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-4999964.onnx",
+                "reward": 0.0,
+                "creation_time": 1727111259.5777035,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-4999964.pt"
+                ]
+            },
+            {
+                "steps": 5499978,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-5499978.onnx",
+                "reward": 0.0,
+                "creation_time": 1727112405.340517,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-5499978.pt"
+                ]
+            },
+            {
+                "steps": 5999978,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-5999978.onnx",
+                "reward": 0.0,
+                "creation_time": 1727113530.1594453,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-5999978.pt"
+                ]
+            },
+            {
+                "steps": 6499982,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-6499982.onnx",
+                "reward": 0.0,
+                "creation_time": 1727114666.9427538,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-6499982.pt"
+                ]
+            },
+            {
+                "steps": 6502722,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-6502722.onnx",
+                "reward": 0.0,
+                "creation_time": 1727114671.574268,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-6502722.pt"
+                ]
+            }
+        ],
+        "elo": 1661.63563851706,
+        "final_checkpoint": {
+            "steps": 6502722,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1727114671.574268,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-6502722.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.0.0",
+        "torch_version": "2.4.1+cu121"
+    }
+}