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: mesa44/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:feb3c40e48b4abce19c9639984d5085dbdc0d3da4ff1b3ae27643b698801a1f8
+size 2820313

SoccerTwos/SoccerTwos-1499156.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e6c8dc9f6f93ec161d2ebc4e6c91e23498868279ba144fad40aad4b7876faa4
+size 2820313

SoccerTwos/SoccerTwos-1499156.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c042007152157bc0a0b5ab118bda78cd2f9359548d861bf0c69f224dffc36fa
+size 34739046

SoccerTwos/SoccerTwos-1999740.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2fe1f30ad2abf24e02cf366b44ae72c52c70b0a4abe894d131a7ec2d3ecf8c5
+size 2820313

SoccerTwos/SoccerTwos-1999740.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53008912015657bddfcd4694e2fa653eab6bd896908e5dc72b6a728b44fbc4a7
+size 34739046

SoccerTwos/SoccerTwos-2499932.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11819ccdc7215b83d8e568a16deb2fd0b67bab3a43224c911a707fdf1e626724
+size 2820313

SoccerTwos/SoccerTwos-2499932.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88198227d145feb782ddb98562ba25b9f487ad8d1f6ea32c218745dafdb1c85a
+size 34739046

SoccerTwos/SoccerTwos-2999556.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feb3c40e48b4abce19c9639984d5085dbdc0d3da4ff1b3ae27643b698801a1f8
+size 2820313

SoccerTwos/SoccerTwos-2999556.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce5a73da189ea6014fdf20fc8c4e223c2b8e4973687f874b05a195ae2f569d0d
+size 34739046

SoccerTwos/SoccerTwos-2999999.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feb3c40e48b4abce19c9639984d5085dbdc0d3da4ff1b3ae27643b698801a1f8
+size 2820313

SoccerTwos/SoccerTwos-2999999.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f041d1702370b5fe4fc0b1b23cd2c9a32fc1ad6352d12efb9c40d599eff16fc6
+size 34739046

SoccerTwos/SoccerTwos-3105550.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eadabe9a5ee0639c554dd51845a44c3e45c8b26ca63119d943b4498350f73ac7
+size 2820313

SoccerTwos/SoccerTwos-3105550.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52bd5b8d4e711d0c0f22f803cf7248d49a5af37c9e29dd3d7f906632f05c6f98
+size 34739046

SoccerTwos/SoccerTwos-999092.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1453d1d1b687dc13b4b6f9f62bf1e9ab9483a485a40d5276453f76206281ec84
+size 2820313

SoccerTwos/SoccerTwos-999092.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:208a962d68c8ae0d88bf82495a2aa4b78adf6e37ac2478492910582cdee4dba6
+size 34738906

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1cd0f45c88ac1152cdf2a9006e796c402527a2fc346a427fd859a69c7d56c85
+size 34737862

SoccerTwos/events.out.tfevents.1715679413.DESKTOP-TALE8L7.5284.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af66f3d7814461e0192d24951de74696de8336f06cbb12b838a31d79d234b374
+size 330763

SoccerTwos/events.out.tfevents.1715760305.DESKTOP-TALE8L7.3880.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dd4eef5d89c511914959372de6c2e7596b1a6ca67a2ea8adbedf083294a83b2
+size 21802

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "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": 0.99, "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": 10000000, "time_horizon": 1048, "summary_freq": 100000, "threaded": false, "self_play": {"save_steps": 70000, "team_change": 210000, "swap_steps": 21000, "window": 20, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-env/SoccerTwos/SoccerTwos.exe", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,84 @@
+default_settings: null
+behaviors:
+  SoccerTwos:
+    trainer_type: poca
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 500000
+    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: 0.99
+        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: 10000000
+    time_horizon: 1048
+    summary_freq: 100000
+    threaded: false
+    self_play:
+      save_steps: 70000
+      team_change: 210000
+      swap_steps: 21000
+      window: 20
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-env/SoccerTwos/SoccerTwos.exe
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  timeout_wait: 60
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: SoccerTwos
+  initialize_from: null
+  load_model: false
+  resume: true
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,291 @@
+Mono path[0] = 'D:/PJ/ml-agents/training-env/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = 'D:/PJ/ml-agents/training-env/SoccerTwos/MonoBleedingEdge/etc'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path D:/PJ/ml-agents/training-env/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  1.253 seconds
+ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Microsoft Media Foundation video decoding to texture disabled: graphics device is Null, only Direct3D 11 and Direct3D 12 (only on desktop) are supported for hardware-accelerated video decoding.
+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: 69.859300 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+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 3 worker threads for Enlighten.
+Memory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [4.0 KB-8.0 KB]: 1 frames, [8.0 KB-16.0 KB]: 2055 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.0 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 246 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 67.0 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 54 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 54 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 54 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 54 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 54 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 488 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 3
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 54 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 54 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 54 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 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 5
+      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 54 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 54 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 54 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 54 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 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 54 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 0.9 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 2057 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 5.0 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 2057 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.4 MB
+      Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.9 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 2056 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]: 2057 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 173.6 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 2
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.9 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 2057 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]: 2056 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 2.2 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 0.9 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 2057 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]: 2056 frames, [2.0 KB-4.0 KB]: 1 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 2.2 KB
+      Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -0,0 +1,368 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 2.480004072189331,
+            "min": 2.3625001907348633,
+            "max": 2.480004072189331,
+            "count": 2
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 519094.59375,
+            "min": 8013.6005859375,
+            "max": 519094.59375,
+            "count": 2
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 291.80232558139534,
+            "min": 38.142857142857146,
+            "max": 291.80232558139534,
+            "count": 2
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 200760.0,
+            "min": 1068.0,
+            "max": 200760.0,
+            "count": 2
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1198.985127360266,
+            "min": 1198.985127360266,
+            "max": 1200.0,
+            "count": 2
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 366889.44897224143,
+            "min": 16800.0,
+            "max": 366889.44897224143,
+            "count": 2
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 3099610.0,
+            "min": 2999999.0,
+            "max": 3099610.0,
+            "count": 2
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 3099610.0,
+            "min": 2999999.0,
+            "max": 3099610.0,
+            "count": 2
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.0024060048162937164,
+            "min": -0.0024060048162937164,
+            "max": 0.08555393666028976,
+            "count": 2
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -0.8252596855163574,
+            "min": -0.8252596855163574,
+            "max": 1.11220121383667,
+            "count": 2
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.00046734767965972424,
+            "min": -0.00046734767965972424,
+            "max": 0.09303981810808182,
+            "count": 2
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -0.16030025482177734,
+            "min": -0.16030025482177734,
+            "max": 1.2095175981521606,
+            "count": 2
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 2
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 2
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.08930029087963327,
+            "min": -0.08930029087963327,
+            "max": 0.2126153799203726,
+            "count": 2
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -30.62999977171421,
+            "min": -30.62999977171421,
+            "max": 2.7639999389648438,
+            "count": 2
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.08930029087963327,
+            "min": -0.08930029087963327,
+            "max": 0.2126153799203726,
+            "count": 2
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -30.62999977171421,
+            "min": -30.62999977171421,
+            "max": 2.7639999389648438,
+            "count": 2
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 2
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 2
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.017513721130793178,
+            "min": 0.017513721130793178,
+            "max": 0.017513721130793178,
+            "count": 1
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.07005488452317271,
+            "min": 0.07005488452317271,
+            "max": 0.07005488452317271,
+            "count": 1
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.02040715963424494,
+            "min": 0.02040715963424494,
+            "max": 0.02040715963424494,
+            "count": 1
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.08162863853697976,
+            "min": 0.08162863853697976,
+            "max": 0.08162863853697976,
+            "count": 1
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.020846690470352768,
+            "min": 0.020846690470352768,
+            "max": 0.020846690470352768,
+            "count": 1
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.08338676188141107,
+            "min": 0.08338676188141107,
+            "max": 0.08338676188141107,
+            "count": 1
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0020840281805323954,
+            "min": 0.0020840281805323954,
+            "max": 0.0020840281805323954,
+            "count": 1
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.008336112722129582,
+            "min": 0.008336112722129582,
+            "max": 0.008336112722129582,
+            "count": 1
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.169467605,
+            "min": 0.169467605,
+            "max": 0.169467605,
+            "count": 1
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.67787042,
+            "min": 0.67787042,
+            "max": 0.67787042,
+            "count": 1
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.0034764334895,
+            "min": 0.0034764334895,
+            "max": 0.0034764334895,
+            "count": 1
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.013905733958,
+            "min": 0.013905733958,
+            "max": 0.013905733958,
+            "count": 1
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1715760297",
+        "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul  5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]",
+        "command_line_arguments": "\\\\?\\C:\\Users\\duyvo\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-env/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.3.0+cpu",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1715760766"
+    },
+    "total": 468.8507794998586,
+    "count": 1,
+    "self": 0.00745509983971715,
+    "children": {
+        "run_training.setup": {
+            "total": 0.1191064000595361,
+            "count": 1,
+            "self": 0.1191064000595361
+        },
+        "TrainerController.start_learning": {
+            "total": 468.72421799995936,
+            "count": 1,
+            "self": 0.15449989144690335,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 11.46295509999618,
+                    "count": 2,
+                    "self": 11.46295509999618
+                },
+                "TrainerController.advance": {
+                    "total": 456.9516715086065,
+                    "count": 6998,
+                    "self": 0.15662221307866275,
+                    "children": {
+                        "env_step": {
+                            "total": 119.13853709911928,
+                            "count": 6998,
+                            "self": 88.1783539133612,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 30.860886494629085,
+                                    "count": 6998,
+                                    "self": 0.9658355887513608,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 29.895050905877724,
+                                            "count": 13708,
+                                            "self": 29.895050905877724
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.0992966911289841,
+                                    "count": 6998,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 400.91223450936377,
+                                            "count": 6998,
+                                            "is_parallel": true,
+                                            "self": 331.3737641153857,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.004783999873325229,
+                                                    "count": 4,
+                                                    "is_parallel": true,
+                                                    "self": 0.0011294996365904808,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.003654500236734748,
+                                                            "count": 16,
+                                                            "is_parallel": true,
+                                                            "self": 0.003654500236734748
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 69.53368639410473,
+                                                    "count": 6998,
+                                                    "is_parallel": true,
+                                                    "self": 3.5871141185052693,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 2.9202786860987544,
+                                                            "count": 6998,
+                                                            "is_parallel": true,
+                                                            "self": 2.9202786860987544
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 51.34761309879832,
+                                                            "count": 6998,
+                                                            "is_parallel": true,
+                                                            "self": 51.34761309879832
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 11.67868049070239,
+                                                            "count": 13996,
+                                                            "is_parallel": true,
+                                                            "self": 2.339395801536739,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 9.339284689165652,
+                                                                    "count": 55984,
+                                                                    "is_parallel": true,
+                                                                    "self": 9.339284689165652
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 337.6565121964086,
+                            "count": 6998,
+                            "self": 1.05021079396829,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 21.97537150257267,
+                                    "count": 6998,
+                                    "self": 21.757783502573147,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.21758799999952316,
+                                            "count": 1,
+                                            "self": 0.21758799999952316
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 314.6309298998676,
+                                    "count": 5,
+                                    "self": 14.940605098148808,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 299.6903248017188,
+                                            "count": 148,
+                                            "self": 299.6903248017188
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.0998919606208801e-06,
+                    "count": 1,
+                    "self": 1.0998919606208801e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.15509040001779795,
+                    "count": 1,
+                    "self": 0.002606899943202734,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.1524835000745952,
+                            "count": 1,
+                            "self": 0.1524835000745952
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,39 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 2999999,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-2999999.onnx",
+                "reward": 0.0,
+                "creation_time": 1715760311.9899578,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-2999999.pt"
+                ]
+            },
+            {
+                "steps": 3105550,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-3105550.onnx",
+                "reward": null,
+                "creation_time": 1715760766.5224805,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-3105550.pt"
+                ]
+            }
+        ],
+        "elo": 1197.935321424963,
+        "final_checkpoint": {
+            "steps": 3105550,
+            "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
+            "reward": null,
+            "creation_time": 1715760766.5224805,
+            "auxillary_file_paths": [
+                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-3105550.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.3.0+cpu"
+    }
+}