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: chaouch/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:a0b0edb2494c514277ca4e08e5cc8614c21d5cfa0ab65608aead03ada3b2e07e
+size 2820313

SoccerTwos/SoccerTwos-15449458.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aefaa6d710dedd22a33c8afb66b308c3d63febbbd20878df7173ac605eb12a3
+size 2820313

SoccerTwos/SoccerTwos-57149996.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f989647978dfdf46072339563fb6ee6d8c2a13c36452f9c7b61eb2f0e22d7e5
+size 2820313

SoccerTwos/SoccerTwos-57149996.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8d942587b947772eb2e68803f178a6506d6864316fe516184c46329826d7d4f
+size 34741042

SoccerTwos/SoccerTwos-57199932.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3cb958fafbff4b4e6206bf7dbf929e8595f416706b651a10d7614d8ea62140a
+size 2820313

SoccerTwos/SoccerTwos-57199932.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfcd22bf7c0556e222feb40010d80b449dc094599af593dd0ad3e363b08f9ea5
+size 34741042

SoccerTwos/SoccerTwos-57249996.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a033887b5c0e176bfe7e65f80f33243463cf44ec1defc539ebb51cb5700bbd80
+size 2820313

SoccerTwos/SoccerTwos-57249996.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7473472e3b05002d0209432c7cf82ce968b98100fe8eb75aec405e8e33d8d1ed
+size 34741042

SoccerTwos/SoccerTwos-57299996.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fd9b5419302c46851e10d07a5841de6e52e7e1f7dc8a2a9c56a128400955411
+size 2820313

SoccerTwos/SoccerTwos-57299996.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d1391641e7095579c48411465cfa8133dfe9e2725af13978c9526bae7307204
+size 34741042

SoccerTwos/SoccerTwos-57321688.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0b0edb2494c514277ca4e08e5cc8614c21d5cfa0ab65608aead03ada3b2e07e
+size 2820313

SoccerTwos/SoccerTwos-57321688.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8f45d894e4bdde37df6956225506b8dff764ea9a52bce7513bcad486fe5c527
+size 34741042

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78df0d8e77b05b495b49302fa71b22eb7f88de43ed8717ee84eed51cfff7eb01
+size 34739782

SoccerTwos/events.out.tfevents.1709290087.uoch-Dell-G15-5511.14839.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22ffdd587fe311822021f2d94fbf7ef25d551f7300d70ef40e9c1efcc52051f0
+size 10445465

SoccerTwos/events.out.tfevents.1709364193.uoch-Dell-G15-5511.5380.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15ea74bed59f480b330c92d805bc353618eb612a5498d348e1a585d27d02a3dd
+size 15952497

SoccerTwos/events.out.tfevents.1709507749.uoch-Dell-G15-5511.3669.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12005184962810214e8dfc6b8e8160c115604f1b07c2bb49cf70fd6827b23d9c
+size 26888419

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0002, "beta": 0.01, "epsilon": 0.25, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "constant"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.973, "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": 100000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 200000, "team_change": 200000, "swap_steps": 2000, "window": 50, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SoccerTwos/SoccerTwos.x86_64", "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": true, "force": false, "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: 0.0002
+      beta: 0.01
+      epsilon: 0.25
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: constant
+    checkpoint_interval: 50000
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 3
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.973
+        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: 100000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 200000
+      team_change: 200000
+      swap_steps: 2000
+      window: 50
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/linux/SoccerTwos/SoccerTwos.x86_64
+  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: 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] = '/home/uoch/ml-agents-release_21/training-envs-executables/linux/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = '/home/uoch/ml-agents-release_21/training-envs-executables/linux/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 /home/uoch/ml-agents-release_21/training-envs-executables/linux/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  0.064 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: 0.433450 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 8 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]: 492220 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 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 14]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.7 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_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 8
+      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 15
+      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 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]: 492221 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]: 492221 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]: 492220 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]: 492221 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]: 492221 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]: 492220 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]: 492221 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]: 492220 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": 1.7387030124664307,
+            "min": 1.602759599685669,
+            "max": 2.2985939979553223,
+            "count": 2616
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 33995.12109375,
+            "min": 29153.87109375,
+            "max": 52195.80078125,
+            "count": 2616
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 67.31506849315069,
+            "min": 42.05128205128205,
+            "max": 98.1,
+            "count": 2616
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19656.0,
+            "min": 11968.0,
+            "max": 21624.0,
+            "count": 2616
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1647.0145821342098,
+            "min": 1523.1757923631521,
+            "max": 1683.1263579667557,
+            "count": 2616
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 240464.12899159463,
+            "min": 161976.6178275062,
+            "max": 375234.1630738749,
+            "count": 2616
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 57319984.0,
+            "min": 31169946.0,
+            "max": 57319984.0,
+            "count": 2616
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 57319984.0,
+            "min": 31169946.0,
+            "max": 57319984.0,
+            "count": 2616
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.026573531329631805,
+            "min": -0.08645182847976685,
+            "max": 0.09884937852621078,
+            "count": 2616
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -3.8797357082366943,
+            "min": -16.723806381225586,
+            "max": 17.298641204833984,
+            "count": 2616
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.026755662634968758,
+            "min": -0.08634110540151596,
+            "max": 0.09761469066143036,
+            "count": 2616
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -3.9063267707824707,
+            "min": -16.491151809692383,
+            "max": 17.082571029663086,
+            "count": 2616
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 2616
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 2616
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.2032150691502715,
+            "min": -0.33299006179252766,
+            "max": 0.3775018179055416,
+            "count": 2616
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -29.669400095939636,
+            "min": -59.488800287246704,
+            "max": 67.87539982795715,
+            "count": 2616
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.2032150691502715,
+            "min": -0.33299006179252766,
+            "max": 0.3775018179055416,
+            "count": 2616
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -29.669400095939636,
+            "min": -59.488800287246704,
+            "max": 67.87539982795715,
+            "count": 2616
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 2616
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 2616
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.018825337445984285,
+            "min": 0.010775110175988327,
+            "max": 0.02479499242811774,
+            "count": 1270
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.018825337445984285,
+            "min": 0.010775110175988327,
+            "max": 0.02479499242811774,
+            "count": 1270
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.0716807467242082,
+            "min": 0.06093314327299595,
+            "max": 0.0890697586039702,
+            "count": 1270
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.0716807467242082,
+            "min": 0.06093314327299595,
+            "max": 0.0890697586039702,
+            "count": 1270
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.07204869166016578,
+            "min": 0.06128497533500195,
+            "max": 0.0895669976870219,
+            "count": 1270
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.07204869166016578,
+            "min": 0.06128497533500195,
+            "max": 0.0895669976870219,
+            "count": 1270
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 8.539211730397e-05,
+            "min": 8.539211730397e-05,
+            "max": 0.000137631183184424,
+            "count": 1270
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 8.539211730397e-05,
+            "min": 8.539211730397e-05,
+            "max": 0.000137631183184424,
+            "count": 1270
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.25,
+            "min": 0.25,
+            "max": 0.25,
+            "count": 1270
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.25,
+            "min": 0.25,
+            "max": 0.25,
+            "count": 1270
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.004275333396999999,
+            "min": 0.004275333396999999,
+            "max": 0.006884676042400002,
+            "count": 1270
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.004275333396999999,
+            "min": 0.004275333396999999,
+            "max": 0.006884676042400002,
+            "count": 1270
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1709507748",
+        "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
+        "command_line_arguments": "/home/uoch/tf/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume",
+        "mlagents_version": "1.0.0",
+        "mlagents_envs_version": "1.0.0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.2.1+cu121",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1709534942"
+    },
+    "total": 27194.501877950002,
+    "count": 1,
+    "self": 0.08062203200097429,
+    "children": {
+        "run_training.setup": {
+            "total": 0.013562335000017356,
+            "count": 1,
+            "self": 0.013562335000017356
+        },
+        "TrainerController.start_learning": {
+            "total": 27194.407693583,
+            "count": 1,
+            "self": 19.885329335604183,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.685746788013603,
+                    "count": 132,
+                    "self": 2.685746788013603
+                },
+                "TrainerController.advance": {
+                    "total": 27171.644558172382,
+                    "count": 1816540,
+                    "self": 20.538421145582106,
+                    "children": {
+                        "env_step": {
+                            "total": 18550.791161325982,
+                            "count": 1816540,
+                            "self": 13707.599330714493,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 4830.228453776381,
+                                    "count": 1816540,
+                                    "self": 138.82647160194665,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 4691.401982174434,
+                                            "count": 3281539,
+                                            "self": 4691.401982174434
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 12.963376835108477,
+                                    "count": 1816539,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 27167.23741055864,
+                                            "count": 1816539,
+                                            "is_parallel": true,
+                                            "self": 15947.144388470559,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.002001161000009688,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.0007302410000988857,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0012709199999108023,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0012709199999108023
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.016199861999950826,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0003734129999202196,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0002923530000202845,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0002923530000202845
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.014475216999983331,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.014475216999983331
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.001058879000026991,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0002293930000405453,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0008294859999864457,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0008294859999864457
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.13682280099931177,
+                                                    "count": 262,
+                                                    "is_parallel": true,
+                                                    "self": 0.026687844031130226,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.11013495696818154,
+                                                            "count": 1048,
+                                                            "is_parallel": true,
+                                                            "self": 0.11013495696818154
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 11219.95619928708,
+                                                    "count": 1816538,
+                                                    "is_parallel": true,
+                                                    "self": 588.137065331217,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 414.8245948215152,
+                                                            "count": 1816538,
+                                                            "is_parallel": true,
+                                                            "self": 414.8245948215152
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 8498.604662810401,
+                                                            "count": 1816538,
+                                                            "is_parallel": true,
+                                                            "self": 8498.604662810401
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 1718.3898763239472,
+                                                            "count": 3633076,
+                                                            "is_parallel": true,
+                                                            "self": 328.77084005874667,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 1389.6190362652005,
+                                                                    "count": 14532304,
+                                                                    "is_parallel": true,
+                                                                    "self": 1389.6190362652005
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 8600.314975700818,
+                            "count": 1816539,
+                            "self": 172.27163687083157,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 3106.2878394979552,
+                                    "count": 1816539,
+                                    "self": 3025.146080364957,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 81.14175913299817,
+                                            "count": 523,
+                                            "self": 81.14175913299817
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 5321.755499332032,
+                                    "count": 1270,
+                                    "self": 2836.8128273619263,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 2484.9426719701055,
+                                            "count": 38100,
+                                            "self": 2484.9426719701055
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.152999175246805e-06,
+                    "count": 1,
+                    "self": 1.152999175246805e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.19205813400185434,
+                    "count": 1,
+                    "self": 0.015921137000987073,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.17613699700086727,
+                            "count": 1,
+                            "self": 0.17613699700086727
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 57149996,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-57149996.onnx",
+                "reward": 0.0,
+                "creation_time": 1709534674.8204062,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-57149996.pt"
+                ]
+            },
+            {
+                "steps": 57199932,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-57199932.onnx",
+                "reward": 0.0,
+                "creation_time": 1709534751.5934513,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-57199932.pt"
+                ]
+            },
+            {
+                "steps": 57249996,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-57249996.onnx",
+                "reward": 0.0,
+                "creation_time": 1709534833.542256,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-57249996.pt"
+                ]
+            },
+            {
+                "steps": 57299996,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-57299996.onnx",
+                "reward": 0.0,
+                "creation_time": 1709534908.9115915,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-57299996.pt"
+                ]
+            },
+            {
+                "steps": 57321688,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-57321688.onnx",
+                "reward": 0.0,
+                "creation_time": 1709534942.8826282,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-57321688.pt"
+                ]
+            }
+        ],
+        "elo": 1651.3269555902784,
+        "final_checkpoint": {
+            "steps": 57321688,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1709534942.8826282,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-57321688.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.0.0",
+        "torch_version": "2.2.1+cu121"
+    }
+}