First Push

README.md

@@ -0,0 +1,31 @@
+
+---
+      tags:
+      - unity-ml-agents
+      - ml-agents
+      - deep-reinforcement-learning
+      - reinforcement-learning
+      - ML-Agents-SoccerTwos
+      library_name: ml-agents
+---
+    
+  # **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://github.com/huggingface/ml-agents#get-started
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+
+
+  ### Resume the training
+  ```
+  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. Go to https://huggingface.co/spaces/unity/ML-Agents-SoccerTwos
+  2. Step 1: Write your model_id: vldnechai/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:e9950e154c60312392a1eb360aca541fe516782184bba258ece9482955045302
+size 1764633

SoccerTwos/SoccerTwos-14499968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d5d1ba8fdc1cd4825679f46beb32ad095e89c52c2170f59e83df3071d0cac97
+size 1764633

SoccerTwos/SoccerTwos-14499968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43e8e6d6d9248321fdcb8b966e6bce0ded7fdffe5dc7c30b63ece0cc34009135
+size 28422481

SoccerTwos/SoccerTwos-14999977.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20d759cc5c0e79118a979d71b2c446dc710f97ddd097bef59705034832f1f6dd
+size 1764633

SoccerTwos/SoccerTwos-14999977.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e0a47ba5006ff9d497a8737c3e2a9e4f53edcd6b4ee994e8f7096728806fcb0
+size 28422481

SoccerTwos/SoccerTwos-15499890.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:113789f541d31a6e77c1c09d7c5b00940bcc740f176c59734d36126b709a97ac
+size 1764633

SoccerTwos/SoccerTwos-15499890.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcc4a22be82a3c0f41398a4656b3e0e3ab49ed6f2681079a71626265515e7781
+size 28422481

SoccerTwos/SoccerTwos-15999956.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b0ecc8ed3d22c82a00f478ee1e320b67f88f445eba0d0d7e17f84697d56956c
+size 1764633

SoccerTwos/SoccerTwos-15999956.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d86d144f6bfc7c59743ba5371e90fe0d917f4d0281434a8048cd262c60cc4552
+size 28422481

SoccerTwos/SoccerTwos-16059224.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9950e154c60312392a1eb360aca541fe516782184bba258ece9482955045302
+size 1764633

SoccerTwos/SoccerTwos-16059224.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faf30ac2df86253c16224ac042f60bbcc147c99ca5a7606f5bdeadf1382b7106
+size 28422481

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faf30ac2df86253c16224ac042f60bbcc147c99ca5a7606f5bdeadf1382b7106
+size 28422481

SoccerTwos/events.out.tfevents.1683042009.MSI.927.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b7a34ffdc07e068862fcfed2fb456c037810031b4256ebd0e54f9705cc34ca1
+size 4107996

SoccerTwos/events.out.tfevents.1683092247.MSI.239.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61d28230fae6d9de11def6443f93cf02e3c9a5bd9a16ae5612f0ad36c03ff069
+size 7812170

SoccerTwos/events.out.tfevents.1683129632.MSI.1077.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01ddfdce970ee9cc847c42b2ea4fddaa5ce20961285c4dca2e5051cddb3fb79e
+size 4441076

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0001, "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": 60000000, "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": 0.55, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos/SoccerTwos.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,82 @@
+default_settings: null
+behaviors:
+  SoccerTwos:
+    trainer_type: poca
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0001
+      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: 60000000
+    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: 0.55
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/SoccerTwos/SoccerTwos.x86_64
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+environment_parameters: null
+checkpoint_settings:
+  run_id: SoccerTwos
+  initialize_from: null
+  load_model: false
+  resume: true
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,324 @@
+Mono path[0] = '/mnt/d/Documents/Projects/hf_rl_course/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = '/mnt/d/Documents/Projects/hf_rl_course/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /mnt/d/Documents/Projects/hf_rl_course/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
+ALSA lib confmisc.c:767:(parse_card) cannot find card '0'
+ALSA lib conf.c:4693:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
+ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:4693:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
+ALSA lib conf.c:4693:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5181:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
+ALSA lib confmisc.c:767:(parse_card) cannot find card '0'
+ALSA lib conf.c:4693:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
+ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:4693:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
+ALSA lib conf.c:4693:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5181:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+FMOD initialized on nosound output
+Begin MonoManager ReloadAssembly
+- Completed reload, in  3.073 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: 0.739700 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
+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]: 81326 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 300.0 KB
+      Peak Allocated Bytes 249.6 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 0.7 KB
+      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_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]: 81327 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 4.9 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 81327 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.2 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]: 81326 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]: 81327 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]: 81327 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]: 81326 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 4.0 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]: 81327 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]: 81326 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": 2.0753798484802246,
+            "min": 1.6941413879394531,
+            "max": 2.123616933822632,
+            "count": 432
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 41441.18359375,
+            "min": 13059.85546875,
+            "max": 48303.5234375,
+            "count": 432
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 57.76744186046512,
+            "min": 45.5607476635514,
+            "max": 85.29310344827586,
+            "count": 432
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19872.0,
+            "min": 5992.0,
+            "max": 21172.0,
+            "count": 432
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1562.370385379922,
+            "min": 1478.0449380077948,
+            "max": 1571.2183482850123,
+            "count": 432
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 268727.7062853466,
+            "min": 85712.8576546484,
+            "max": 331772.55834787374,
+            "count": 432
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 16049992.0,
+            "min": 11739974.0,
+            "max": 16049992.0,
+            "count": 432
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 16049992.0,
+            "min": 11739974.0,
+            "max": 16049992.0,
+            "count": 432
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": 0.011824635788798332,
+            "min": -0.12827473878860474,
+            "max": 0.08283628523349762,
+            "count": 432
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": 2.022012710571289,
+            "min": -23.987377166748047,
+            "max": 12.673952102661133,
+            "count": 432
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.011609936133027077,
+            "min": -0.12794987857341766,
+            "max": 0.08335159718990326,
+            "count": 432
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 1.9852991104125977,
+            "min": -23.92662811279297,
+            "max": 12.75279426574707,
+            "count": 432
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 432
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 432
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.020430409420303434,
+            "min": -0.3276352956014521,
+            "max": 0.31089248374707434,
+            "count": 432
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -3.493600010871887,
+            "min": -63.08319973945618,
+            "max": 53.784399688243866,
+            "count": 432
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.020430409420303434,
+            "min": -0.3276352956014521,
+            "max": 0.31089248374707434,
+            "count": 432
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -3.493600010871887,
+            "min": -63.08319973945618,
+            "max": 53.784399688243866,
+            "count": 432
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 432
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 432
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.019133638390000367,
+            "min": 0.009504728168637181,
+            "max": 0.024814592476468535,
+            "count": 209
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.019133638390000367,
+            "min": 0.009504728168637181,
+            "max": 0.024814592476468535,
+            "count": 209
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.10119041601816813,
+            "min": 0.089591034501791,
+            "max": 0.1190962294737498,
+            "count": 209
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.10119041601816813,
+            "min": 0.089591034501791,
+            "max": 0.1190962294737498,
+            "count": 209
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.1021848164498806,
+            "min": 0.09043613796432813,
+            "max": 0.12001427635550499,
+            "count": 209
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.1021848164498806,
+            "min": 0.09043613796432813,
+            "max": 0.12001427635550499,
+            "count": 209
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 9.999999999999998e-05,
+            "min": 9.999999999999998e-05,
+            "max": 9.999999999999998e-05,
+            "count": 209
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 9.999999999999998e-05,
+            "min": 9.999999999999998e-05,
+            "max": 9.999999999999998e-05,
+            "count": 209
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 209
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 209
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 209
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 209
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1683129627",
+        "python_version": "3.9.0 (default, Nov 15 2020, 14:28:56) \n[GCC 7.3.0]",
+        "command_line_arguments": "/home/vld/anaconda3/envs/hf_rl_course/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.11.0+cu102",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1683149722"
+    },
+    "total": 20095.0709115,
+    "count": 1,
+    "self": 0.14871449999918696,
+    "children": {
+        "run_training.setup": {
+            "total": 0.050549100000353064,
+            "count": 1,
+            "self": 0.050549100000353064
+        },
+        "TrainerController.start_learning": {
+            "total": 20094.8716479,
+            "count": 1,
+            "self": 6.860395402669383,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 10.521520900008909,
+                    "count": 23,
+                    "self": 10.521520900008909
+                },
+                "TrainerController.advance": {
+                    "total": 20077.00831859732,
+                    "count": 299972,
+                    "self": 6.951193199689442,
+                    "children": {
+                        "env_step": {
+                            "total": 14850.574014399841,
+                            "count": 299972,
+                            "self": 5623.9756530980085,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 9222.60552849892,
+                                    "count": 299972,
+                                    "self": 41.12715460173058,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 9181.47837389719,
+                                            "count": 542182,
+                                            "self": 9181.47837389719
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 3.9928328029127442,
+                                    "count": 299972,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 20073.40502370076,
+                                            "count": 299972,
+                                            "is_parallel": true,
+                                            "self": 15156.218758199837,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.003249000001233071,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.0009197999970638193,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0023292000041692518,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0023292000041692518
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.04167540000344161,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.000604000008024741,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0005910000036237761,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0005910000036237761
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.038517299995874055,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.038517299995874055
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0019630999959190376,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004978000069968402,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0014652999889221974,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0014652999889221974
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.034217100001114886,
+                                                    "count": 44,
+                                                    "is_parallel": true,
+                                                    "self": 0.007301599987840746,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.02691550001327414,
+                                                            "count": 176,
+                                                            "is_parallel": true,
+                                                            "self": 0.02691550001327414
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 4917.152048400923,
+                                                    "count": 299971,
+                                                    "is_parallel": true,
+                                                    "self": 154.68728360757814,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 106.43757610006287,
+                                                            "count": 299971,
+                                                            "is_parallel": true,
+                                                            "self": 106.43757610006287
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 4179.489904796239,
+                                                            "count": 299971,
+                                                            "is_parallel": true,
+                                                            "self": 4179.489904796239
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 476.5372838970434,
+                                                            "count": 599942,
+                                                            "is_parallel": true,
+                                                            "self": 103.17700669672922,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 373.36027720031416,
+                                                                    "count": 2399768,
+                                                                    "is_parallel": true,
+                                                                    "self": 373.36027720031416
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 5219.4831109977895,
+                            "count": 299972,
+                            "self": 47.44477459735208,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 3497.633985700464,
+                                    "count": 299972,
+                                    "self": 3494.4295499004656,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 3.204435799998464,
+                                            "count": 9,
+                                            "self": 3.204435799998464
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 1674.4043506999733,
+                                    "count": 210,
+                                    "self": 628.5340833001101,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 1045.8702673998632,
+                                            "count": 6292,
+                                            "self": 1045.8702673998632
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.0000003385357559e-06,
+                    "count": 1,
+                    "self": 1.0000003385357559e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.4814120000010007,
+                    "count": 1,
+                    "self": 0.1450870999979088,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.3363249000030919,
+                            "count": 1,
+                            "self": 0.3363249000030919
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 14499968,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-14499968.onnx",
+                "reward": 0.0,
+                "creation_time": 1683142486.8463593,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-14499968.pt"
+                ]
+            },
+            {
+                "steps": 14999977,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-14999977.onnx",
+                "reward": 0.0,
+                "creation_time": 1683144790.4017015,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-14999977.pt"
+                ]
+            },
+            {
+                "steps": 15499890,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-15499890.onnx",
+                "reward": 0.0,
+                "creation_time": 1683147108.0883424,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-15499890.pt"
+                ]
+            },
+            {
+                "steps": 15999956,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-15999956.onnx",
+                "reward": 0.0,
+                "creation_time": 1683149451.8418515,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-15999956.pt"
+                ]
+            },
+            {
+                "steps": 16059224,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-16059224.onnx",
+                "reward": null,
+                "creation_time": 1683149721.9208179,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-16059224.pt"
+                ]
+            }
+        ],
+        "elo": 1558.469964620246,
+        "final_checkpoint": {
+            "steps": 16059224,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": null,
+            "creation_time": 1683149721.9208179,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-16059224.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}