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: hythyt/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 sha256:531668938c36bf5f46b1e9723fd2db199556688e4de01eecd75f50014f82d2e8
+size 650646

SnowballTarget/SnowballTarget-1599976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b027f8aad56e84a7b525dd9a19c77ad955554d4f25d492ec16ef17a55aed187d
+size 650646

SnowballTarget/SnowballTarget-1599976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:680e7e7f39f5237e9fe19b9d246d80f7f36a7dfa098af1b0337bd57774d173da
+size 3850214

SnowballTarget/SnowballTarget-1649992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14ecc25b0658069ffaed9eb279695c248543a70ed2552b5b4cb48c629123d692
+size 650646

SnowballTarget/SnowballTarget-1649992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8f6e2ef32c06aec3c1957ce32d1bcb7178bc43ee370f5ca7ff1748e5ef6b834
+size 3850214

SnowballTarget/SnowballTarget-1699936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cb11061bda67db5af60c450ee70a6526a4f9acace9391d775f03e35635eca0c
+size 650646

SnowballTarget/SnowballTarget-1699936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4551245317f761f3013ab01109913fea82c1e2e8358028a4607f9181f20192be
+size 3850214

SnowballTarget/SnowballTarget-1749960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a03dc668de3b584cbd9a19efa52bf97162a4bd0482060f46dabf2652b720df8
+size 650646

SnowballTarget/SnowballTarget-1749960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff6297b88e969230b422433233e22a7dc99618def7243663063d8220432b578f
+size 3850214

SnowballTarget/SnowballTarget-1799984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1bd5f67ea1a25df9dc6c12febe06e1649a87f9b4dd62faa81ebfb5dad3b2d04
+size 650646

SnowballTarget/SnowballTarget-1799984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de4538a9d1aded25d5a9226c73eb7069b4520ea2f16d0dbf213cc97579bfb3ea
+size 3850214

SnowballTarget/SnowballTarget-1849984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b4c3899c88e8876708a60b9bdd9022f176944b402102c6ff343e2169bd15860
+size 650646

SnowballTarget/SnowballTarget-1849984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9c3c923454ca6f6ffa0770ee4916e9b2b548539f72622c826c5b7e5c886e844
+size 3850214

SnowballTarget/SnowballTarget-1899944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b91cd0f840385305c8e6aa1d407b72645d1077b79963d7b6a5ba3cf86a3ed192
+size 650646

SnowballTarget/SnowballTarget-1899944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6f6dbdeda014aaec07220d61b4fdb1bf3e186a0df02bd5846bda3530dc9e1a9
+size 3850214

SnowballTarget/SnowballTarget-1949968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db5222ff8a467777e10888176ae6117dad743ba0ff28b322fdc1dbd1e87c90c6
+size 650646

SnowballTarget/SnowballTarget-1949968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0ebb8c678c699f42dee829c8eb039a0cbceea298211befd0e652bb442622392
+size 3850214

SnowballTarget/SnowballTarget-1999992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:531668938c36bf5f46b1e9723fd2db199556688e4de01eecd75f50014f82d2e8
+size 650646

SnowballTarget/SnowballTarget-1999992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f386e23e2e0a5cad83aeb581b8cc293805a13d59a21a72b64d45cd7f78ad4cc
+size 3850214

SnowballTarget/SnowballTarget-2000376.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:531668938c36bf5f46b1e9723fd2db199556688e4de01eecd75f50014f82d2e8
+size 650646

SnowballTarget/SnowballTarget-2000376.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b1e178fba2fa7a5daccad122af8a21d71f5876e8f74d6ecf4f63f3a52b9a3a3
+size 3850214

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e0e0bdc131eebf344379d3a61f6d92e20da1b9eca35a4b51d25c6027b526b8d
+size 3849250

SnowballTarget/events.out.tfevents.1708250996.e320c1ae9d88.4392.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a39c7a44ba3665aea7700011f3ad89c11c6ddaa7aa3fb7f8a3c5e0a631b8bd7
+size 170625

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": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 2000000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64", "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": true, "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: 50000
+    network_settings:
+      normalize: false
+      hidden_units: 256
+      num_layers: 2
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+    init_path: null
+    keep_checkpoints: 10
+    even_checkpoints: false
+    max_steps: 2000000
+    time_horizon: 64
+    summary_freq: 10000
+    threaded: true
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64
+  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: true
+  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  0.092 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: 0.719196 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]: 53652 frames, [16.0 KB-32.0 KB]: 909 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 43
+    [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]: 10923 frames, [8.0 MB-16.0 MB]: 28736 frames, [16.0 MB-32.0 MB]: 14903 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 2
+      Peak Allocated memory 24.5 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 54562 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.5 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]: 53202 frames, [64.0 KB-128.0 KB]: 1360 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 66.8 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 54562 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]: 54562 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]: 54561 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]: 54562 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]: 54562 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 +1,377 @@
+{
+    "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 0.4676729142665863,
+            "min": 0.4647047519683838,
+            "max": 2.860957622528076,
+            "count": 200
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 4820.3046875,
+            "min": 4443.64892578125,
+            "max": 29299.06640625,
+            "count": 200
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 1999992.0,
+            "min": 9952.0,
+            "max": 1999992.0,
+            "count": 200
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 1999992.0,
+            "min": 9952.0,
+            "max": 1999992.0,
+            "count": 200
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 14.382729530334473,
+            "min": 0.3005019724369049,
+            "max": 14.529829025268555,
+            "count": 200
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2948.45947265625,
+            "min": 58.29738235473633,
+            "max": 2953.619140625,
+            "count": 200
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 200
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 10945.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 200
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06954078151137247,
+            "min": 0.05987668705290394,
+            "max": 0.0779010560600927,
+            "count": 200
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.34770390755686237,
+            "min": 0.23950674821161577,
+            "max": 0.38950528030046355,
+            "count": 200
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.15490547938674104,
+            "min": 0.10773771084552887,
+            "max": 0.2927440986329434,
+            "count": 200
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.7745273969337052,
+            "min": 0.4309508433821155,
+            "max": 1.290336033292845,
+            "count": 200
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 7.032997656000039e-07,
+            "min": 7.032997656000039e-07,
+            "max": 0.00029918820027059994,
+            "count": 200
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 3.5164988280000196e-06,
+            "min": 3.5164988280000196e-06,
+            "max": 0.0014885160038279998,
+            "count": 200
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10023440000000002,
+            "min": 0.10023440000000002,
+            "max": 0.1997294,
+            "count": 200
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.5011720000000001,
+            "min": 0.4029176,
+            "max": 0.996172,
+            "count": 200
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 2.1696560000000067e-05,
+            "min": 2.1696560000000067e-05,
+            "max": 0.004986497059999999,
+            "count": 200
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.00010848280000000034,
+            "min": 0.00010848280000000034,
+            "max": 0.024808982800000004,
+            "count": 200
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 28.327272727272728,
+            "min": 3.1136363636363638,
+            "max": 28.68888888888889,
+            "count": 200
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1558.0,
+            "min": 137.0,
+            "max": 1566.0,
+            "count": 200
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 28.327272727272728,
+            "min": 3.1136363636363638,
+            "max": 28.68888888888889,
+            "count": 200
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1558.0,
+            "min": 137.0,
+            "max": 1566.0,
+            "count": 200
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 200
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 200
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1708250995",
+        "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn /content/SnowballTarget.yaml --env=/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics --force",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.2.0+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1708255306"
+    },
+    "total": 4311.35360025,
+    "count": 1,
+    "self": 0.489965753999968,
+    "children": {
+        "run_training.setup": {
+            "total": 0.04945148699994206,
+            "count": 1,
+            "self": 0.04945148699994206
+        },
+        "TrainerController.start_learning": {
+            "total": 4310.814183009001,
+            "count": 1,
+            "self": 5.416347300897542,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 3.177165125999977,
+                    "count": 1,
+                    "self": 3.177165125999977
+                },
+                "TrainerController.advance": {
+                    "total": 4302.1299164341035,
+                    "count": 181871,
+                    "self": 2.7885790082082167,
+                    "children": {
+                        "env_step": {
+                            "total": 4299.341337425895,
+                            "count": 181871,
+                            "self": 2792.538878100863,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 1503.858034825993,
+                                    "count": 181871,
+                                    "self": 14.365423254102552,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 1489.4926115718904,
+                                            "count": 181871,
+                                            "self": 1489.4926115718904
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 2.9444244990396555,
+                                    "count": 181871,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 4299.949203287,
+                                            "count": 181871,
+                                            "is_parallel": true,
+                                            "self": 2105.834313281929,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0054633480000347845,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.003968197000062901,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0014951509999718837,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0014951509999718837
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.03804084800003693,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006361370001286559,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0004009770000266144,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004009770000266144
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.034934837999912816,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.034934837999912816
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.002068895999968845,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003935549997322596,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0016753410002365854,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0016753410002365854
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 2194.114890005071,
+                                                    "count": 181870,
+                                                    "is_parallel": true,
+                                                    "self": 104.23997799010476,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 51.85728597907166,
+                                                            "count": 181870,
+                                                            "is_parallel": true,
+                                                            "self": 51.85728597907166
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1708.3360449078327,
+                                                            "count": 181870,
+                                                            "is_parallel": true,
+                                                            "self": 1708.3360449078327
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 329.681581128062,
+                                                            "count": 181870,
+                                                            "is_parallel": true,
+                                                            "self": 60.352540434002776,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 269.32904069405924,
+                                                                    "count": 1818700,
+                                                                    "is_parallel": true,
+                                                                    "self": 269.32904069405924
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.0003272719995948137,
+                    "count": 1,
+                    "self": 0.0003272719995948137,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 4249.562116208759,
+                                    "count": 6459827,
+                                    "is_parallel": true,
+                                    "self": 134.71285545272985,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 2332.078997726028,
+                                            "count": 6459827,
+                                            "is_parallel": true,
+                                            "self": 2326.039195259027,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 6.039802467000527,
+                                                    "count": 40,
+                                                    "is_parallel": true,
+                                                    "self": 6.039802467000527
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 1782.7702630300018,
+                                            "count": 909,
+                                            "is_parallel": true,
+                                            "self": 505.36145151994447,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 1277.4088115100574,
+                                                    "count": 46356,
+                                                    "is_parallel": true,
+                                                    "self": 1277.4088115100574
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.09042687600049248,
+                    "count": 1,
+                    "self": 0.0010059430005640024,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.08942093299992848,
+                            "count": 1,
+                            "self": 0.08942093299992848
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 1599976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1599976.onnx",
+                "reward": 27.636363636363637,
+                "creation_time": 1708254453.5691857,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1599976.pt"
+                ]
+            },
+            {
+                "steps": 1649992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1649992.onnx",
+                "reward": 27.7,
+                "creation_time": 1708254561.7073584,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1649992.pt"
+                ]
+            },
+            {
+                "steps": 1699936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1699936.onnx",
+                "reward": 27.636363636363637,
+                "creation_time": 1708254669.6805897,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1699936.pt"
+                ]
+            },
+            {
+                "steps": 1749960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1749960.onnx",
+                "reward": 27.90909090909091,
+                "creation_time": 1708254776.4041853,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1749960.pt"
+                ]
+            },
+            {
+                "steps": 1799984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1799984.onnx",
+                "reward": 27.90909090909091,
+                "creation_time": 1708254884.3785455,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1799984.pt"
+                ]
+            },
+            {
+                "steps": 1849984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1849984.onnx",
+                "reward": 28.272727272727273,
+                "creation_time": 1708254989.5875938,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1849984.pt"
+                ]
+            },
+            {
+                "steps": 1899944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1899944.onnx",
+                "reward": 27.181818181818183,
+                "creation_time": 1708255095.6929421,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1899944.pt"
+                ]
+            },
+            {
+                "steps": 1949968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1949968.onnx",
+                "reward": 28.0,
+                "creation_time": 1708255201.7594125,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1949968.pt"
+                ]
+            },
+            {
+                "steps": 1999992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1999992.onnx",
+                "reward": 28.272727272727273,
+                "creation_time": 1708255306.2773032,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1999992.pt"
+                ]
+            },
+            {
+                "steps": 2000376,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-2000376.onnx",
+                "reward": 28.272727272727273,
+                "creation_time": 1708255306.4143176,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-2000376.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 2000376,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 28.272727272727273,
+            "creation_time": 1708255306.4143176,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-2000376.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.2.0+cu121"
+    }
+}