ML-Agents-SnowballTarget 1st

README.md

@@ -0,0 +1,31 @@
+
+---
+      tags:
+      - unity-ml-agents
+      - ml-agents
+      - deep-reinforcement-learning
+      - reinforcement-learning
+      - ML-Agents-SnowballTarget
+      library_name: ml-agents
+---
+    
+  # **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://github.com/huggingface/ml-agents#get-started
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+
+
+  ### Resume the training
+  ```
+  mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
+  ```
+  ### Watch your Agent play
+  You can watch your agent **playing directly in your browser:**.
+  
+  1. Go to https://huggingface.co/spaces/unity/ML-Agents-SnowballTarget
+  2. Step 1: Write your model_id: LeonardoMdSA/ML-Agents-SnowballTarget
+  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:c6155d0e6e5f1530ae8c42ada427ac459e633785d221e4ff78f736611b34a936
+size 645119

SnowballTarget/SnowballTarget-1000208.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6155d0e6e5f1530ae8c42ada427ac459e633785d221e4ff78f736611b34a936
+size 645119

SnowballTarget/SnowballTarget-1000208.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7866459b7604a6db18f6471aa58ce0ac36613e958c5a72543b6ee26522235d27
+size 3845822

SnowballTarget/SnowballTarget-899992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6809fd32b43e233b3ea52e0e5fa6f5f4e566a71a7183a2c451d7eae21ef4e4ec
+size 645119

SnowballTarget/SnowballTarget-899992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb905bc5b969615f2cee8e5dcb810f696891c5c5769458cc8e8de11f77f1042b
+size 3845822

SnowballTarget/SnowballTarget-999952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6155d0e6e5f1530ae8c42ada427ac459e633785d221e4ff78f736611b34a936
+size 645119

SnowballTarget/SnowballTarget-999952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:162c51e0ce007f2fbdd09778ec0143d19239058e7fd0fe104b6314f0f159becf
+size 3845822

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7866459b7604a6db18f6471aa58ce0ac36613e958c5a72543b6ee26522235d27
+size 3845822

SnowballTarget/events.out.tfevents.1767446689.7022762c74c9.8.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24b4ed66bd45fb64218c5362b769f82e5e48d1dc29a2a4845dcc135686adbf22
+size 89011

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 512, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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": 3, "checkpoint_interval": 100000, "max_steps": 1000000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "2026-01-03_13-24-45", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "./src/runs/train"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,75 @@
+default_settings: null
+behaviors:
+  SnowballTarget:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 512
+      buffer_size: 2048
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    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: 3
+    checkpoint_interval: 100000
+    max_steps: 1000000
+    time_horizon: 64
+    summary_freq: 10000
+    threaded: true
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+environment_parameters: null
+checkpoint_settings:
+  run_id: 2026-01-03_13-24-45
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: ./src/runs/train
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,293 @@
+Mono path[0] = '/workspace/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/workspace/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
+PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
+Unable to load player prefs
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /workspace/ml-agents/training-envs-executables/linux/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
+FMOD initialized on nosound output
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.091 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: 0.913005 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 6 worker threads for Enlighten.
+Memory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [8.0 KB-16.0 KB]: 26830 frames, [16.0 KB-32.0 KB]: 454 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 202 B
+      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_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_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 3.6 KB
+      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 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_EnlightenWorker] x 6
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 11
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 9]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      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 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 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 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 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 41
+    [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]: 11284 frames, [8.0 MB-16.0 MB]: 16001 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 2
+      Peak Allocated memory 14.6 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 27285 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 1.0 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 26110 frames, [64.0 KB-128.0 KB]: 1175 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 66.4 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 27285 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]: 27285 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]: 27284 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 3.5 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]: 27285 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]: 27285 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 +1,384 @@
+{
+    "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 0.6983682513237,
+            "min": 0.6623551249504089,
+            "max": 2.8813538551330566,
+            "count": 100
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 6898.4814453125,
+            "min": 6338.73828125,
+            "max": 29571.333984375,
+            "count": 100
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 999952.0,
+            "min": 9952.0,
+            "max": 999952.0,
+            "count": 100
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 999952.0,
+            "min": 9952.0,
+            "max": 999952.0,
+            "count": 100
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 13.740630149841309,
+            "min": 0.15224452316761017,
+            "max": 13.842514038085938,
+            "count": 100
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2679.4228515625,
+            "min": 29.535438537597656,
+            "max": 2837.71533203125,
+            "count": 100
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 100
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 8756.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 100
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.030044385471228452,
+            "min": 0.02360446234039652,
+            "max": 0.041371952805396475,
+            "count": 100
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.12017754188491381,
+            "min": 0.09441784936158608,
+            "max": 0.2016947714534278,
+            "count": 100
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.18033633598436913,
+            "min": 0.10405897271508971,
+            "max": 0.3607084912558397,
+            "count": 100
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.7213453439374765,
+            "min": 0.41623589086035884,
+            "max": 1.7100629806518557,
+            "count": 100
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 1.3764995412000023e-06,
+            "min": 1.3764995412000023e-06,
+            "max": 0.00029837640054119997,
+            "count": 100
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 5.505998164800009e-06,
+            "min": 5.505998164800009e-06,
+            "max": 0.001477032007656,
+            "count": 100
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10045880000000001,
+            "min": 0.10045880000000001,
+            "max": 0.19945880000000002,
+            "count": 100
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.40183520000000006,
+            "min": 0.40183520000000006,
+            "max": 0.992344,
+            "count": 100
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 3.289412000000005e-05,
+            "min": 3.289412000000005e-05,
+            "max": 0.00497299412,
+            "count": 100
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0001315764800000002,
+            "min": 0.0001315764800000002,
+            "max": 0.0246179656,
+            "count": 100
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 26.91111111111111,
+            "min": 2.659090909090909,
+            "max": 27.636363636363637,
+            "count": 100
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1211.0,
+            "min": 117.0,
+            "max": 1496.0,
+            "count": 100
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 26.91111111111111,
+            "min": 2.659090909090909,
+            "max": 27.636363636363637,
+            "count": 100
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1211.0,
+            "min": 117.0,
+            "max": 1496.0,
+            "count": 100
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 100
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 100
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1767446688",
+        "python_version": "3.8.8 (default, Feb 24 2021, 21:46:12) \n[GCC 7.3.0]",
+        "command_line_arguments": "/opt/conda/bin/mlagents-learn ./src/SnowballTarget_params.yaml --env=ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=2026-01-03_13-24-45 --results-dir=./src/runs/train --no-graphics",
+        "mlagents_version": "0.29.0.dev0",
+        "mlagents_envs_version": "0.29.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.8.1",
+        "numpy_version": "1.19.2",
+        "end_time_seconds": "1767448812"
+    },
+    "total": 2123.259687265,
+    "count": 1,
+    "self": 0.38329621200091424,
+    "children": {
+        "run_training.setup": {
+            "total": 0.043761259999882895,
+            "count": 1,
+            "self": 0.043761259999882895
+        },
+        "TrainerController.start_learning": {
+            "total": 2122.8326297929993,
+            "count": 1,
+            "self": 2.264165933996537,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 4.805450693999774,
+                    "count": 1,
+                    "self": 4.805450693999774
+                },
+                "TrainerController.advance": {
+                    "total": 2115.593958942003,
+                    "count": 90947,
+                    "self": 1.142850004056072,
+                    "children": {
+                        "env_step": {
+                            "total": 2114.451108937947,
+                            "count": 90947,
+                            "self": 1213.1186439977073,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 900.1915419552092,
+                                    "count": 90947,
+                                    "self": 5.790881330321554,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 894.4006606248877,
+                                            "count": 90947,
+                                            "self": 224.13459771971475,
+                                            "children": {
+                                                "TorchPolicy.sample_actions": {
+                                                    "total": 670.2660629051729,
+                                                    "count": 90947,
+                                                    "self": 670.2660629051729
+                                                }
+                                            }
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 1.1409229850305564,
+                                    "count": 90947,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 2118.3036810700814,
+                                            "count": 90947,
+                                            "is_parallel": true,
+                                            "self": 1054.7076118050272,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0022466709997388534,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0010523089995331247,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0011943620002057287,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0011943620002057287
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.02143639899986738,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00023757300004945137,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00018875399973694584,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00018875399973694584
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.01984742800004824,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.01984742800004824
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.001162644000032742,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0002073619998554932,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0009552820001772488,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0009552820001772488
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1063.5960692650542,
+                                                    "count": 90946,
+                                                    "is_parallel": true,
+                                                    "self": 22.3981307589238,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 13.233283371182097,
+                                                            "count": 90946,
+                                                            "is_parallel": true,
+                                                            "self": 13.233283371182097
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 929.8114113069737,
+                                                            "count": 90946,
+                                                            "is_parallel": true,
+                                                            "self": 929.8114113069737
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 98.15324382797462,
+                                                            "count": 90946,
+                                                            "is_parallel": true,
+                                                            "self": 15.926496355072231,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 82.22674747290239,
+                                                                    "count": 909460,
+                                                                    "is_parallel": true,
+                                                                    "self": 82.22674747290239
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.00014741999984835275,
+                    "count": 1,
+                    "self": 0.00014741999984835275,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 2105.487785272931,
+                                    "count": 1821371,
+                                    "is_parallel": true,
+                                    "self": 29.744525839172184,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 1548.4716573037554,
+                                            "count": 1821371,
+                                            "is_parallel": true,
+                                            "self": 1545.2616951397563,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 3.20996216399908,
+                                                    "count": 10,
+                                                    "is_parallel": true,
+                                                    "self": 3.20996216399908
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 527.2716021300034,
+                                            "count": 454,
+                                            "is_parallel": true,
+                                            "self": 203.5452611520227,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 323.7263409779807,
+                                                    "count": 5448,
+                                                    "is_parallel": true,
+                                                    "self": 323.7263409779807
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.16890680300002714,
+                    "count": 1,
+                    "self": 0.025944785000319825,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.1429620179997073,
+                            "count": 1,
+                            "self": 0.1429620179997073
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,47 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 899992,
+                "file_path": "./src/runs/train/2026-01-03_13-24-45/SnowballTarget/SnowballTarget-899992.onnx",
+                "reward": 25.454545454545453,
+                "creation_time": 1767448596.3416429,
+                "auxillary_file_paths": [
+                    "./src/runs/train/2026-01-03_13-24-45/SnowballTarget/SnowballTarget-899992.pt"
+                ]
+            },
+            {
+                "steps": 999952,
+                "file_path": "./src/runs/train/2026-01-03_13-24-45/SnowballTarget/SnowballTarget-999952.onnx",
+                "reward": 27.09090909090909,
+                "creation_time": 1767448811.5070314,
+                "auxillary_file_paths": [
+                    "./src/runs/train/2026-01-03_13-24-45/SnowballTarget/SnowballTarget-999952.pt"
+                ]
+            },
+            {
+                "steps": 1000208,
+                "file_path": "./src/runs/train/2026-01-03_13-24-45/SnowballTarget/SnowballTarget-1000208.onnx",
+                "reward": 27.09090909090909,
+                "creation_time": 1767448811.702544,
+                "auxillary_file_paths": [
+                    "./src/runs/train/2026-01-03_13-24-45/SnowballTarget/SnowballTarget-1000208.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 1000208,
+            "file_path": "./src/runs/train/2026-01-03_13-24-45/SnowballTarget.onnx",
+            "reward": 27.09090909090909,
+            "creation_time": 1767448811.702544,
+            "auxillary_file_paths": [
+                "./src/runs/train/2026-01-03_13-24-45/SnowballTarget/SnowballTarget-1000208.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.29.0.dev0",
+        "torch_version": "1.8.1"
+    }
+}