Push to Hub

README.md

@@ -0,0 +1,35 @@
+---
+library_name: ml-agents
+tags:
+- SnowballTarget
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-SnowballTarget
+---
+
+  # **ppo** Agent playing **SnowballTarget**
+  This is a trained model of a **ppo** agent playing **SnowballTarget**
+  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: Asheron/SnowballTargetWSL-test1
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

SnowballTarget.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01f9be5aaa3819b59cb16589481394bf3bc465fd48600636f0f4b50854e17250
+size 650646

SnowballTarget/SnowballTarget-10208.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01f9be5aaa3819b59cb16589481394bf3bc465fd48600636f0f4b50854e17250
+size 650646

SnowballTarget/SnowballTarget-10208.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62ef0378e5fb23fe252b4162132ea8af3b99a382148400393a8919e4fbd4b58d
+size 3850000

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d28c486e9a4f6ac91d9c576d489fa9d373928441fb857f2b0fbc90499610ee1
+size 3849250

SnowballTarget/events.out.tfevents.1701566222.David-main.9612.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45a28667c5192cc9792b8b1bf2c13a9ccce5f02e03b542fd39d9469b39dd8e48
+size 23730

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 512, "buffer_size": 8182, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "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": 10, "even_checkpoints": false, "max_steps": 10000, "time_horizon": 64, "summary_freq": 1000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SnowballTarget/SnowballTarget", "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": "SnowballTargetWSL-test1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,79 @@
+default_settings: null
+behaviors:
+  SnowballTarget:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 512
+      buffer_size: 8182
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 50000
+    network_settings:
+      normalize: false
+      hidden_units: 256
+      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: 10
+    even_checkpoints: false
+    max_steps: 10000
+    time_horizon: 64
+    summary_freq: 1000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/SnowballTarget/SnowballTarget
+  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: SnowballTargetWSL-test1
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,349 @@
+Mono path[0] = '/home/dfotland/projects/wsl-reinforce/gymnasium-ml-agents/training-envs-executables/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/home/dfotland/projects/wsl-reinforce/gymnasium-ml-agents/training-envs-executables/SnowballTarget/SnowballTarget_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/dfotland/projects/wsl-reinforce/gymnasium-ml-agents/training-envs-executables/SnowballTarget/SnowballTarget_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  0.034 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' - 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: 0.363118 ms
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+requesting resize 84 x 84
+Setting up 12 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]: 274 frames, [16.0 KB-32.0 KB]: 4 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_Job.Worker 18]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 304.0 KB
+      Peak Allocated Bytes 228.9 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_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_Job.Worker 16]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      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 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 14]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 17]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      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_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_AssetGarbageCollectorHelper] x 23
+      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_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_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 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      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 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 20]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 11]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      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_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 21]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      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_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 13]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 12
+      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 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_Job.Worker 22]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 9]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 8]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 10]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 15]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 12]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 19]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 264 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 29
+    [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]: 279 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 5.3 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 279 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.6 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]: 252 frames, [64.0 KB-128.0 KB]: 27 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: [32.0 KB-64.0 KB]: 279 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 39.6 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]: 279 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]: 278 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 1.0 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 279 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]: 279 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.7 KB
+      Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -0,0 +1,355 @@
+{
+    "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 2.890129804611206,
+            "min": 2.890129804611206,
+            "max": 2.890331506729126,
+            "count": 10
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 2034.6513671875,
+            "min": 2034.6513671875,
+            "max": 4323.92919921875,
+            "count": 10
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 9952.0,
+            "min": 960.0,
+            "max": 9952.0,
+            "count": 10
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 9952.0,
+            "min": 960.0,
+            "max": 9952.0,
+            "count": 10
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.1443396359682083,
+            "min": -0.02502424642443657,
+            "max": 0.1443396359682083,
+            "count": 10
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2.1650946140289307,
+            "min": -0.6256061792373657,
+            "max": 2.1650946140289307,
+            "count": 10
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 10
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 10
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 4
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 2189.0,
+            "min": 2189.0,
+            "max": 2189.0,
+            "count": 4
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 2.5454545454545454,
+            "min": 2.1818181818181817,
+            "max": 3.090909090909091,
+            "count": 4
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 28.0,
+            "min": 24.0,
+            "max": 34.0,
+            "count": 4
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 2.5454545454545454,
+            "min": 2.1818181818181817,
+            "max": 3.090909090909091,
+            "count": 4
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 28.0,
+            "min": 24.0,
+            "max": 34.0,
+            "count": 4
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.034890227926000224,
+            "min": 0.034890227926000224,
+            "max": 0.034890227926000224,
+            "count": 1
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.034890227926000224,
+            "min": 0.034890227926000224,
+            "max": 0.034890227926000224,
+            "count": 1
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.09762346715319391,
+            "min": 0.09762346715319391,
+            "max": 0.09762346715319391,
+            "count": 1
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.09762346715319391,
+            "min": 0.09762346715319391,
+            "max": 0.09762346715319391,
+            "count": 1
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 3.864008712000001e-05,
+            "min": 3.864008712000001e-05,
+            "max": 3.864008712000001e-05,
+            "count": 1
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 3.864008712000001e-05,
+            "min": 3.864008712000001e-05,
+            "max": 3.864008712000001e-05,
+            "count": 1
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.11287999999999998,
+            "min": 0.11287999999999998,
+            "max": 0.11287999999999998,
+            "count": 1
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.11287999999999998,
+            "min": 0.11287999999999998,
+            "max": 0.11287999999999998,
+            "count": 1
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.0006527120000000002,
+            "min": 0.0006527120000000002,
+            "max": 0.0006527120000000002,
+            "count": 1
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0006527120000000002,
+            "min": 0.0006527120000000002,
+            "max": 0.0006527120000000002,
+            "count": 1
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1701566222",
+        "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
+        "command_line_arguments": "/home/dfotland/projects/wsl-reinforce/gymnasium-ml-agents/venv-ml-agents/bin/mlagents-learn ./config/SnowballTarget.yaml --env=./training-envs-executables/SnowballTarget/SnowballTarget --run-id=SnowballTargetWSL-test1 --no-graphics",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.1.1+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1701566239"
+    },
+    "total": 17.199973239010433,
+    "count": 1,
+    "self": 0.2171839510265272,
+    "children": {
+        "run_training.setup": {
+            "total": 0.009799769992241636,
+            "count": 1,
+            "self": 0.009799769992241636
+        },
+        "TrainerController.start_learning": {
+            "total": 16.972989517991664,
+            "count": 1,
+            "self": 0.00869064818834886,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 0.7239282900118269,
+                    "count": 1,
+                    "self": 0.7239282900118269
+                },
+                "TrainerController.advance": {
+                    "total": 16.16393009980675,
+                    "count": 928,
+                    "self": 0.008159256947692484,
+                    "children": {
+                        "env_step": {
+                            "total": 12.537758856313303,
+                            "count": 928,
+                            "self": 6.365368775499519,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 6.166461443179287,
+                                    "count": 928,
+                                    "self": 0.030128593993140385,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 6.136332849186147,
+                                            "count": 928,
+                                            "self": 6.136332849186147
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.005928637634497136,
+                                    "count": 928,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 16.826006932911696,
+                                            "count": 928,
+                                            "is_parallel": true,
+                                            "self": 11.035792209702777,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.001130607008235529,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0003167200193274766,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0008138869889080524,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0008138869889080524
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.01490170499891974,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.000168889993801713,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00021973898401483893,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00021973898401483893
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.014041069021914154,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.014041069021914154
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0004720069991890341,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0001227590546477586,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0003492479445412755,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0003492479445412755
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 5.790214723208919,
+                                                    "count": 927,
+                                                    "is_parallel": true,
+                                                    "self": 0.1281979820341803,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 0.06885534862522036,
+                                                            "count": 927,
+                                                            "is_parallel": true,
+                                                            "self": 0.06885534862522036
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 5.234773067117203,
+                                                            "count": 927,
+                                                            "is_parallel": true,
+                                                            "self": 5.234773067117203
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 0.35838832543231547,
+                                                            "count": 927,
+                                                            "is_parallel": true,
+                                                            "self": 0.07572059534140863,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.28266773009090684,
+                                                                    "count": 9270,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.28266773009090684
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 3.6180119865457527,
+                            "count": 928,
+                            "self": 0.01151119646965526,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 1.1729432440770324,
+                                    "count": 928,
+                                    "self": 1.1729432440770324
+                                },
+                                "_update_policy": {
+                                    "total": 2.433557545999065,
+                                    "count": 1,
+                                    "self": 0.6060042819590308,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 1.8275532640400343,
+                                            "count": 51,
+                                            "self": 1.8275532640400343
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 5.53991412743926e-07,
+                    "count": 1,
+                    "self": 5.53991412743926e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.07643992599332705,
+                    "count": 1,
+                    "self": 0.00040903297485783696,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.07603089301846921,
+                            "count": 1,
+                            "self": 0.07603089301846921
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,29 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 10208,
+                "file_path": "results/SnowballTargetWSL-test1/SnowballTarget/SnowballTarget-10208.onnx",
+                "reward": 2.5454545454545454,
+                "creation_time": 1701566239.4687564,
+                "auxillary_file_paths": [
+                    "results/SnowballTargetWSL-test1/SnowballTarget/SnowballTarget-10208.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 10208,
+            "file_path": "results/SnowballTargetWSL-test1/SnowballTarget.onnx",
+            "reward": 2.5454545454545454,
+            "creation_time": 1701566239.4687564,
+            "auxillary_file_paths": [
+                "results/SnowballTargetWSL-test1/SnowballTarget/SnowballTarget-10208.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.1.1+cu121"
+    }
+}