First Push

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: HuggingMachines/ppo-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:f82c6f936cde27368df1b4bf642ff365a77cecaf5a5a412df446412360d5e2f4
+size 657877

SnowballTarget/SnowballTarget-2112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beb6acd2bb572021af5d562b0a9ebab1b550db27463a2d4871ff33eb29b0c327
+size 656971

SnowballTarget/SnowballTarget-2112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a334a2683c5c1510f45fef3ed11cde51bb864ca8d2b7c6a637c0b2a12dd2046a
+size 1308616

SnowballTarget/SnowballTarget-599952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea186e19678af8a097fa3d7d7cc8e6b9996cf90cbadbffe32bd649b1ddbf8b12
+size 657877

SnowballTarget/SnowballTarget-599952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85c261b28412e1d2a21d353794d85e96d8ed2bb8ff1e166764260947daf5f9ba
+size 3872655

SnowballTarget/SnowballTarget-649976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e94f1af38c7062f08a4b65c25f9f070b5edf3998919e07058a416f2c3ccf906a
+size 657877

SnowballTarget/SnowballTarget-649976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c942eb12d91a64716bfb71d7bace48c556a3ab5380398610abd17b0a9bb97f26
+size 3872655

SnowballTarget/SnowballTarget-699936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9177217d2e7e7e6492600c8b8e4176586905b4ca8f86da159e29959c1478b38c
+size 657877

SnowballTarget/SnowballTarget-699936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9d7f748b2a1228d89ab20f0b6a79d31187384acb3624b7348072dff9a9ea3ae
+size 3872655

SnowballTarget/SnowballTarget-700128.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f82c6f936cde27368df1b4bf642ff365a77cecaf5a5a412df446412360d5e2f4
+size 657877

SnowballTarget/SnowballTarget-700128.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17c0ce2beece4eafb41affad8eb458bea24b73948df7dd3cf356237bd6d3ef02
+size 3872655

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a28f5dd8937bff42f3f3417b162d0a971f3cab1127bb33e57c06f1d6acdceed8
+size 3871478

SnowballTarget/events.out.tfevents.1765049308.db65d0e7949e.4735.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80bdbf0e59cb244ef618d097c6692a01693cd694e8dd5e3f3f920a32e22bd672
+size 14880

SnowballTarget/events.out.tfevents.1765049900.db65d0e7949e.7311.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07ff22c9057b46735aad7ee0f996f26016f3c62e853859da6aab263af4992135
+size 1113

SnowballTarget/events.out.tfevents.1765049964.db65d0e7949e.7630.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acf848a0e74ecb01e1e56197bea14d284e924650844cbcda362eef9ff56a4651
+size 9381

SnowballTarget/events.out.tfevents.1765051356.db65d0e7949e.13602.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc5c7e2da3e645a5ecdb5c8e30a14ccad9e9e90ba988e5337e4ba09e262ee731
+size 13443

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 256, "buffer_size": 2048, "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": true, "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": 4, "even_checkpoints": false, "max_steps": 700000, "time_horizon": 64, "summary_freq": 20000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/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": "SnowballTarget1", "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 +1,79 @@
+default_settings: null
+behaviors:
+  SnowballTarget:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 256
+      buffer_size: 2048
+      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: true
+      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: 4
+    even_checkpoints: false
+    max_steps: 700000
+    time_horizon: 64
+    summary_freq: 20000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/linux/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: SnowballTarget1
+  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 +1,259 @@
+Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/content/ml-agents/training-envs-executables/linux/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 /content/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
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+FMOD initialized on nosound output
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.097 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: 0.756331 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 1 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]: 8043 frames, [16.0 KB-32.0 KB]: 136 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 198 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_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 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 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_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]
+      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]
+      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_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_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]: 8180 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 8.0 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 8180 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.2 MB
+      Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 8033 frames, [64.0 KB-128.0 KB]: 147 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]: 8180 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]: 8180 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]: 8179 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]: 8180 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]: 8180 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 +1,362 @@
+{
+    "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 0.849920392036438,
+            "min": 0.8069454431533813,
+            "max": 0.8786962032318115,
+            "count": 15
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 16828.423828125,
+            "min": 16193.92578125,
+            "max": 18016.787109375,
+            "count": 15
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 699936.0,
+            "min": 419992.0,
+            "max": 699936.0,
+            "count": 15
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 699936.0,
+            "min": 419992.0,
+            "max": 699936.0,
+            "count": 15
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 14.376312255859375,
+            "min": 13.69563102722168,
+            "max": 14.376312255859375,
+            "count": 15
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 5736.1484375,
+            "min": 5368.6875,
+            "max": 5807.10546875,
+            "count": 15
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.04974580502446905,
+            "min": 0.04285651367657313,
+            "max": 0.05344135037443333,
+            "count": 15
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.44771224522022146,
+            "min": 0.38570862308915815,
+            "max": 0.48528646325242636,
+            "count": 15
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.16737105604261163,
+            "min": 0.1584306804256307,
+            "max": 0.2147602600355943,
+            "count": 15
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 1.5063395043835046,
+            "min": 1.425876123830676,
+            "max": 1.9328423403203487,
+            "count": 15
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 4.056098647999997e-06,
+            "min": 4.056098647999997e-06,
+            "max": 0.00012379891587657144,
+            "count": 15
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 3.650488783199997e-05,
+            "min": 3.650488783199997e-05,
+            "max": 0.001114190242889143,
+            "count": 15
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.101352,
+            "min": 0.101352,
+            "max": 0.14126628571428573,
+            "count": 15
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.912168,
+            "min": 0.912168,
+            "max": 1.2713965714285715,
+            "count": 15
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 7.746479999999995e-05,
+            "min": 7.746479999999995e-05,
+            "max": 0.002069187657142857,
+            "count": 15
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0006971831999999995,
+            "min": 0.0006971831999999995,
+            "max": 0.018622688914285715,
+            "count": 15
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 15
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 19701.0,
+            "min": 19701.0,
+            "max": 21890.0,
+            "count": 15
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 28.2020202020202,
+            "min": 26.694736842105264,
+            "max": 28.2020202020202,
+            "count": 15
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 2792.0,
+            "min": 2536.0,
+            "max": 2982.0,
+            "count": 15
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 28.2020202020202,
+            "min": 26.694736842105264,
+            "max": 28.2020202020202,
+            "count": 15
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 2792.0,
+            "min": 2536.0,
+            "max": 2982.0,
+            "count": 15
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 15
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 15
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1765051355",
+        "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.8.0+cu128",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1765052166"
+    },
+    "total": 811.095951625,
+    "count": 1,
+    "self": 0.9339186759998483,
+    "children": {
+        "run_training.setup": {
+            "total": 0.02745952400027818,
+            "count": 1,
+            "self": 0.02745952400027818
+        },
+        "TrainerController.start_learning": {
+            "total": 810.1345734249999,
+            "count": 1,
+            "self": 0.7897105160268438,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.8735850279999795,
+                    "count": 1,
+                    "self": 2.8735850279999795
+                },
+                "TrainerController.advance": {
+                    "total": 806.2926777669727,
+                    "count": 27264,
+                    "self": 0.7776902450095804,
+                    "children": {
+                        "env_step": {
+                            "total": 614.5986771189073,
+                            "count": 27264,
+                            "self": 470.6666514869321,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 143.42557077898073,
+                                    "count": 27264,
+                                    "self": 2.4565840349691825,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 140.96898674401154,
+                                            "count": 27264,
+                                            "self": 140.96898674401154
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.5064548529944659,
+                                    "count": 27264,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 806.6488648819268,
+                                            "count": 27264,
+                                            "is_parallel": true,
+                                            "self": 395.7431057329668,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.002360758000122587,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006580539993592538,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0017027040007633332,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0017027040007633332
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.086901601000136,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006693960003758548,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.000463283000044612,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.000463283000044612
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.0795213619999231,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0795213619999231
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.006247559999792429,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0034369569993941695,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0028106030003982596,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0028106030003982596
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 410.90575914896,
+                                                    "count": 27263,
+                                                    "is_parallel": true,
+                                                    "self": 18.421328414990967,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 9.948173833980036,
+                                                            "count": 27263,
+                                                            "is_parallel": true,
+                                                            "self": 9.948173833980036
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 316.5323121510296,
+                                                            "count": 27263,
+                                                            "is_parallel": true,
+                                                            "self": 316.5323121510296
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 66.00394474895938,
+                                                            "count": 27263,
+                                                            "is_parallel": true,
+                                                            "self": 11.638041289069406,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 54.36590345988998,
+                                                                    "count": 272630,
+                                                                    "is_parallel": true,
+                                                                    "self": 54.36590345988998
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 190.91631040305583,
+                            "count": 27264,
+                            "self": 1.0692236440149827,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 70.5709728070392,
+                                    "count": 27264,
+                                    "self": 69.70160377103912,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.8693690360000801,
+                                            "count": 6,
+                                            "self": 0.8693690360000801
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 119.27611395200165,
+                                    "count": 136,
+                                    "self": 65.56878470301626,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 53.70732924898539,
+                                            "count": 3264,
+                                            "self": 53.70732924898539
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.2880000213044696e-06,
+                    "count": 1,
+                    "self": 1.2880000213044696e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.17859882600032506,
+                    "count": 1,
+                    "self": 0.0016665440007272991,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.17693228199959776,
+                            "count": 1,
+                            "self": 0.17693228199959776
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,56 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 599952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-599952.onnx",
+                "reward": 28.363636363636363,
+                "creation_time": 1765051897.2577991,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-599952.pt"
+                ]
+            },
+            {
+                "steps": 649976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-649976.onnx",
+                "reward": 27.90909090909091,
+                "creation_time": 1765052030.8418453,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-649976.pt"
+                ]
+            },
+            {
+                "steps": 699936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-699936.onnx",
+                "reward": 28.727272727272727,
+                "creation_time": 1765052165.5967824,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-699936.pt"
+                ]
+            },
+            {
+                "steps": 700128,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-700128.onnx",
+                "reward": 28.727272727272727,
+                "creation_time": 1765052165.8229582,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-700128.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 700128,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 28.727272727272727,
+            "creation_time": 1765052165.8229582,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-700128.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.8.0+cu128"
+    }
+}