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: granenko/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:b0ae4e2766a8398cdff19d217a3d6d8d32d9c1a1f4ffa75ea7871238555c2f2b
+size 650646

SnowballTarget/SnowballTarget-119952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfa5bc45c9eac7a10f7d474b3dba50375777a5fdae186403f94bd11413fb40db
+size 650646

SnowballTarget/SnowballTarget-119952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b0e52469ad3b724d0ba7f49f8e53c75b0129adffc691a9d88767050d9d10ac0
+size 3850564

SnowballTarget/SnowballTarget-139944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c65146e4f6d0a90209e2a6b5f0a37d11716a0a34689d0bd9df485d90ac730e5
+size 650646

SnowballTarget/SnowballTarget-139944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f9eadf188034cc6b68a8597ff47f70b22f5e44735e6e97a12a3617d39da54b7
+size 3850564

SnowballTarget/SnowballTarget-159936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6a3681c1cc032c5ee2c56d2b80bc5a7875cd74be0c6b9372adf2f57792c4589
+size 650646

SnowballTarget/SnowballTarget-159936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b1c7c4d9c6ea6ce081c8e4c638c9dbfbd0b18240c3a516fc0e359edb5a43611
+size 3850564

SnowballTarget/SnowballTarget-170104.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0ae4e2766a8398cdff19d217a3d6d8d32d9c1a1f4ffa75ea7871238555c2f2b
+size 650646

SnowballTarget/SnowballTarget-170104.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba16ddf2b8e66b86e007d8f18c78f0f5892b3a64f5cc4dd75c5e9964c0e90283
+size 3850564

SnowballTarget/SnowballTarget-19992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43af4778b67567598a46ac2d4feffa08aaeac468cbddf8c85eef499c913c2efc
+size 650646

SnowballTarget/SnowballTarget-19992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9a9d40da984ebd5567f09b85ca282aee72da25f54f05dac4efbbbd85f759d2d
+size 3850487

SnowballTarget/SnowballTarget-39984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7361b857fec1184a86342deb337942f78224d001a3eae8ffa1c96a98d4915fc
+size 650646

SnowballTarget/SnowballTarget-39984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9912a0978d19a5946053d80af0e38393769cf91e56efa8807b36d4b30b40542
+size 3850487

SnowballTarget/SnowballTarget-59976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16efeca1df6e20e237e0f75d03ef32edbf73fdd677f8fcfc2d573dd4adce26d0
+size 650646

SnowballTarget/SnowballTarget-59976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ee97faf0d5cc414d1803c473f2b3da8891a408f87cdb9334ca28bebd9359d23
+size 3850487

SnowballTarget/SnowballTarget-79968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb9dfed7b51e811bb5796f314b5c9db4d117599c73e2410276229b759b76ff0c
+size 650646

SnowballTarget/SnowballTarget-79968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6172918152d458b67dfd1b962211b2b7572981e92b5cba39f467b8717b9bdff9
+size 3850487

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0facd96fd3f5c34d50b174696061e0768e4cf95262a85457e7f244e08ad2c70
+size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09df7050d24a9667750cada7c8412f246c6004578c1466f9cc764d05bb150f5f
+size 3850487

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f3e0b10a7b21d6982a4d41b10ad1f0497710231489e85fde3e98e4dffea7d11
+size 3849717

SnowballTarget/events.out.tfevents.1757957600.cd33790e2025.6162.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:753ebacd8efc17766d7e2d5cf5e7c5d009c1f6c1132ff27d7f64bf02ef8a319e
+size 26174

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "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": 20000, "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": 170000, "time_horizon": 64, "summary_freq": 10000, "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": 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: 128
+      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: 20000
+    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: 170000
+    time_horizon: 64
+    summary_freq: 10000
+    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: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,262 @@
+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'
+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 /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  0.086 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: 0.639012 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]: 4562 frames, [16.0 KB-32.0 KB]: 77 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 42
+    [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]: 4640 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 6.6 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 4640 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.7 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]: 4220 frames, [64.0 KB-128.0 KB]: 420 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]: 4640 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]: 4640 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]: 4639 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]: 4640 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]: 4640 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": 1.1591025590896606,
+            "min": 1.1591025590896606,
+            "max": 2.8643639087677,
+            "count": 17
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 11118.111328125,
+            "min": 11118.111328125,
+            "max": 29239.427734375,
+            "count": 17
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 169976.0,
+            "min": 9952.0,
+            "max": 169976.0,
+            "count": 17
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 169976.0,
+            "min": 9952.0,
+            "max": 169976.0,
+            "count": 17
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 12.330113410949707,
+            "min": 0.6275967359542847,
+            "max": 12.330113410949707,
+            "count": 17
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2527.67333984375,
+            "min": 121.7537612915039,
+            "max": 2527.67333984375,
+            "count": 17
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06710609917876462,
+            "min": 0.06406728350203576,
+            "max": 0.0757081382069052,
+            "count": 17
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.33553049589382306,
+            "min": 0.25626913400814305,
+            "max": 0.37090685595210426,
+            "count": 17
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.21298438556054058,
+            "min": 0.11686520335406028,
+            "max": 0.28211189222102073,
+            "count": 17
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 1.064921927802703,
+            "min": 0.4674608134162411,
+            "max": 1.4105594611051038,
+            "count": 17
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 8.978920536470583e-06,
+            "min": 8.978920536470583e-06,
+            "max": 0.0002904494149482353,
+            "count": 17
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 4.489460268235292e-05,
+            "min": 4.489460268235292e-05,
+            "max": 0.0013648941626823526,
+            "count": 17
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10299294117647059,
+            "min": 0.10299294117647059,
+            "max": 0.19681647058823531,
+            "count": 17
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.514964705882353,
+            "min": 0.4352658823529413,
+            "max": 0.954964705882353,
+            "count": 17
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.00015934776470588233,
+            "min": 0.00015934776470588233,
+            "max": 0.004841141882352941,
+            "count": 17
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0007967388235294116,
+            "min": 0.0007967388235294116,
+            "max": 0.022752738823529413,
+            "count": 17
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 17
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 10945.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 17
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 24.527272727272727,
+            "min": 3.090909090909091,
+            "max": 24.75,
+            "count": 17
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1349.0,
+            "min": 136.0,
+            "max": 1349.0,
+            "count": 17
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 24.527272727272727,
+            "min": 3.090909090909091,
+            "max": 24.75,
+            "count": 17
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1349.0,
+            "min": 136.0,
+            "max": 1349.0,
+            "count": 17
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 17
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 17
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1757957599",
+        "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",
+        "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": "1757957971"
+    },
+    "total": 371.278641158,
+    "count": 1,
+    "self": 0.42972936900014247,
+    "children": {
+        "run_training.setup": {
+            "total": 0.025705669999979364,
+            "count": 1,
+            "self": 0.025705669999979364
+        },
+        "TrainerController.start_learning": {
+            "total": 370.8232061189999,
+            "count": 1,
+            "self": 0.3443921460011552,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 3.1064313079998556,
+                    "count": 1,
+                    "self": 3.1064313079998556
+                },
+                "TrainerController.advance": {
+                    "total": 367.27709929299886,
+                    "count": 15464,
+                    "self": 0.3324291569788329,
+                    "children": {
+                        "env_step": {
+                            "total": 261.510216093008,
+                            "count": 15464,
+                            "self": 201.30239721599833,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 60.00797852400865,
+                                    "count": 15464,
+                                    "self": 1.1016091830081223,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 58.90636934100053,
+                                            "count": 15464,
+                                            "self": 58.90636934100053
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.19984035300103642,
+                                    "count": 15464,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 369.6811520329859,
+                                            "count": 15464,
+                                            "is_parallel": true,
+                                            "self": 193.15463715097917,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.005853120999972816,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.004337254000347457,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0015158669996253593,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0015158669996253593
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.03503240999998525,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005408750000697182,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0003927990001102444,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003927990001102444
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.0322879779998857,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0322879779998857
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0018107579999195877,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00033934099974430865,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.001471417000175279,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.001471417000175279
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 176.52651488200672,
+                                                    "count": 15463,
+                                                    "is_parallel": true,
+                                                    "self": 8.31920321898997,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 4.505316354989645,
+                                                            "count": 15463,
+                                                            "is_parallel": true,
+                                                            "self": 4.505316354989645
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 137.16799236901807,
+                                                            "count": 15463,
+                                                            "is_parallel": true,
+                                                            "self": 137.16799236901807
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 26.534002939009042,
+                                                            "count": 15463,
+                                                            "is_parallel": true,
+                                                            "self": 4.745211895038665,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 21.788791043970377,
+                                                                    "count": 154630,
+                                                                    "is_parallel": true,
+                                                                    "self": 21.788791043970377
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 105.43445404301201,
+                            "count": 15464,
+                            "self": 0.4443695120191933,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 23.028450066994083,
+                                    "count": 15464,
+                                    "self": 22.281292824993443,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.7471572420006396,
+                                            "count": 8,
+                                            "self": 0.7471572420006396
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 81.96163446399873,
+                                    "count": 77,
+                                    "self": 33.54951859100561,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 48.41211587299313,
+                                            "count": 3924,
+                                            "self": 48.41211587299313
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 8.639999578008428e-07,
+                    "count": 1,
+                    "self": 8.639999578008428e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.09528250800008209,
+                    "count": 1,
+                    "self": 0.0009033930000441615,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.09437911500003793,
+                            "count": 1,
+                            "self": 0.09437911500003793
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,101 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 19992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-19992.onnx",
+                "reward": 8.090909090909092,
+                "creation_time": 1757957648.646702,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-19992.pt"
+                ]
+            },
+            {
+                "steps": 39984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-39984.onnx",
+                "reward": 11.636363636363637,
+                "creation_time": 1757957693.1371741,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-39984.pt"
+                ]
+            },
+            {
+                "steps": 59976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-59976.onnx",
+                "reward": 14.545454545454545,
+                "creation_time": 1757957736.791914,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-59976.pt"
+                ]
+            },
+            {
+                "steps": 79968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-79968.onnx",
+                "reward": 19.545454545454547,
+                "creation_time": 1757957781.220337,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-79968.pt"
+                ]
+            },
+            {
+                "steps": 99960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 21.272727272727273,
+                "creation_time": 1757957823.7526844,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                ]
+            },
+            {
+                "steps": 119952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-119952.onnx",
+                "reward": 22.90909090909091,
+                "creation_time": 1757957865.7105267,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-119952.pt"
+                ]
+            },
+            {
+                "steps": 139944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-139944.onnx",
+                "reward": 23.727272727272727,
+                "creation_time": 1757957907.8270817,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-139944.pt"
+                ]
+            },
+            {
+                "steps": 159936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-159936.onnx",
+                "reward": 25.181818181818183,
+                "creation_time": 1757957950.458592,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-159936.pt"
+                ]
+            },
+            {
+                "steps": 170104,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-170104.onnx",
+                "reward": 25.727272727272727,
+                "creation_time": 1757957970.682035,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-170104.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 170104,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 25.727272727272727,
+            "creation_time": 1757957970.682035,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-170104.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.8.0+cu128"
+    }
+}