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: SparkleDark/SnowPark
+  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 sha256:0c029f30def6947d892d9561c02043eb69081216bda4a68f2a4ed11c400843f2
+size 1823189

SnowballTarget/SnowballTarget-1000208.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c029f30def6947d892d9561c02043eb69081216bda4a68f2a4ed11c400843f2
+size 1823189

SnowballTarget/SnowballTarget-1000208.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d585a69b6a67a0832c074daf4a80de62ece2a72b18d353408f525d6f07bb2270
+size 10842703

SnowballTarget/SnowballTarget-200112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d36bffcddc88c5e4f6e0aa24be71a7e285c29379529f84512b530f3a4a711057
+size 650646

SnowballTarget/SnowballTarget-200112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b8b3dbd47c578500570d4d44f96e358e66c27223861a0a26dc2cecc5d53415a
+size 3850075

SnowballTarget/SnowballTarget-599936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6317824d85c49c52217e927248183cabb35b4111bfab10154e40040aa1bc5f40
+size 1823189

SnowballTarget/SnowballTarget-599936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8a48524dc3aec7d6d43d669d8ead896a6d4476f58451d3b86341ee72c2acb7a
+size 10842534

SnowballTarget/SnowballTarget-649960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fbe7356ef58bb9841c42303995be4f90d0e208af2fe7355e31dcf6678e487ea
+size 1823189

SnowballTarget/SnowballTarget-649960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b93db332b6c787561ca488bba63bcd772ed37453b50fa9f13e55c01c7ed110af
+size 10842534

SnowballTarget/SnowballTarget-699984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ff1d5ea903a901d90247228dbbdd986623128cf5a1e66873f33575822496ff4
+size 1823189

SnowballTarget/SnowballTarget-699984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65ef2a56728b0d13e79d37c873f9e9f80cf6e00e3d0418ecc9e419624710c732
+size 10842534

SnowballTarget/SnowballTarget-749984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08ca826417f3099473fa3d650c290e7b60065291aed54a40a6e22232b4531a36
+size 1823189

SnowballTarget/SnowballTarget-749984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39930d2ddf3ed5e88aed8c68eaa32b91111dedf9fd41073eb3e31b326dcd399e
+size 10842534

SnowballTarget/SnowballTarget-799944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9acd70c0fa25ce038f966d337145fdb1e5e62cb54a76375a212d5cf92375ee27
+size 1823189

SnowballTarget/SnowballTarget-799944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f835cd7134179fe1e092d42e6d8da43e3bee6a8a8f1318cd32c63a8401e491c
+size 10842534

SnowballTarget/SnowballTarget-849968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc0cc1030c0764dc4649f358748b7b47e58bff21f47d2f8ede270749636816dd
+size 1823189

SnowballTarget/SnowballTarget-849968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bbe7fd458e1a79b5c22ea84071c7859939880f08e2583867b626e4f3b57acc1
+size 10842534

SnowballTarget/SnowballTarget-899992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd888dce9506e506f02f3f0117275f5672f1c73b6be8d90f9d89ee218c8c80ce
+size 1823189

SnowballTarget/SnowballTarget-899992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1334cde18c3edb1ae4eaf0425c6b7c02d41f55cdd14ca6eb83fd7727de49af6a
+size 10842534

SnowballTarget/SnowballTarget-949992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:657dea03529ffdf8d780f5976b19ebc4a82a47748d3e679a595d6d1217711058
+size 1823189

SnowballTarget/SnowballTarget-949992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff7d968f23d0a2d082bd5575367bcb89125e4191f889ad6b3a739315df0d489e
+size 10842534

SnowballTarget/SnowballTarget-999952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b8902f507d59f827684c97e8fc6dcd33f3e233b5bd69ffd702c9cb8cb9a4499
+size 1823189

SnowballTarget/SnowballTarget-999952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85aa2c61c08759cea847f2701b3c3d8d00af7194dc2918e1e913bf3cae7d2c15
+size 10842534

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5e6587b8e6543acf35e384255ec831882e53d4793656c37c3e5c9fc84ec5f5c
+size 10841379

SnowballTarget/events.out.tfevents.1711886860.93bc7f3a7112.11989.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aef09edf1f4965c57b6d07380a2b2d1a56b5e58b7d1937d26f7e6cd455c7f8d9
+size 88069

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": 4, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": true, "hidden_units": 512, "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": 1000000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "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": 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: 4
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 50000
+    network_settings:
+      normalize: true
+      hidden_units: 512
+      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: 1000000
+    time_horizon: 64
+    summary_freq: 10000
+    threaded: true
+    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: true
+  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  0.086 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: 0.630350 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]: 26827 frames, [16.0 KB-32.0 KB]: 454 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.0 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 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 44
+    [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]: 11024 frames, [8.0 MB-16.0 MB]: 16258 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 2
+      Peak Allocated memory 14.5 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 27282 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.8 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]: 26661 frames, [64.0 KB-128.0 KB]: 621 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 66.3 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 27282 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]: 27282 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]: 27281 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]: 27282 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]: 27282 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": 0.8081425428390503,
+            "min": 0.7938821315765381,
+            "max": 2.8456103801727295,
+            "count": 100
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 7671.697265625,
+            "min": 7623.32470703125,
+            "max": 29267.1015625,
+            "count": 100
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 999952.0,
+            "min": 9952.0,
+            "max": 999952.0,
+            "count": 100
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 999952.0,
+            "min": 9952.0,
+            "max": 999952.0,
+            "count": 100
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 14.954306602478027,
+            "min": 0.4316805899143219,
+            "max": 15.026077270507812,
+            "count": 100
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2916.08984375,
+            "min": 83.74603271484375,
+            "max": 3068.86181640625,
+            "count": 100
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 100
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 8756.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 100
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06826501792554208,
+            "min": 0.058823206797409086,
+            "max": 0.07924564501664623,
+            "count": 100
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.27306007170216834,
+            "min": 0.23529282718963634,
+            "max": 0.37043796652869787,
+            "count": 100
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.12304429597604799,
+            "min": 0.10341359151198584,
+            "max": 0.28494547674541965,
+            "count": 100
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.49217718390419196,
+            "min": 0.45335718726410584,
+            "max": 1.302776433965739,
+            "count": 100
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 1.3764995412000027e-06,
+            "min": 1.3764995412000027e-06,
+            "max": 0.00029837640054119997,
+            "count": 100
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 5.505998164800011e-06,
+            "min": 5.505998164800011e-06,
+            "max": 0.0014770320076559996,
+            "count": 100
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10045880000000001,
+            "min": 0.10045880000000001,
+            "max": 0.1994588,
+            "count": 100
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.40183520000000006,
+            "min": 0.40183520000000006,
+            "max": 0.992344,
+            "count": 100
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 3.289412000000005e-05,
+            "min": 3.289412000000005e-05,
+            "max": 0.00497299412,
+            "count": 100
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0001315764800000002,
+            "min": 0.0001315764800000002,
+            "max": 0.024617965600000007,
+            "count": 100
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 29.511111111111113,
+            "min": 3.5681818181818183,
+            "max": 29.6,
+            "count": 100
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1328.0,
+            "min": 157.0,
+            "max": 1626.0,
+            "count": 100
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 29.511111111111113,
+            "min": 3.5681818181818183,
+            "max": 29.6,
+            "count": 100
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1328.0,
+            "min": 157.0,
+            "max": 1626.0,
+            "count": 100
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 100
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 100
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1711886859",
+        "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.2.1+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1711889266"
+    },
+    "total": 2406.944137318,
+    "count": 1,
+    "self": 0.5906470800000534,
+    "children": {
+        "run_training.setup": {
+            "total": 0.052162992999910784,
+            "count": 1,
+            "self": 0.052162992999910784
+        },
+        "TrainerController.start_learning": {
+            "total": 2406.301327245,
+            "count": 1,
+            "self": 2.7372133419517013,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.971740643999965,
+                    "count": 1,
+                    "self": 1.971740643999965
+                },
+                "TrainerController.advance": {
+                    "total": 2401.4341183300485,
+                    "count": 90938,
+                    "self": 1.3246895810912065,
+                    "children": {
+                        "env_step": {
+                            "total": 2400.1094287489573,
+                            "count": 90938,
+                            "self": 1577.625548316989,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 820.8810756259618,
+                                    "count": 90938,
+                                    "self": 7.194135596123033,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 813.6869400298388,
+                                            "count": 90938,
+                                            "self": 813.6869400298388
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 1.6028048060065885,
+                                    "count": 90938,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 2400.2347397529825,
+                                            "count": 90938,
+                                            "is_parallel": true,
+                                            "self": 1320.6365935919653,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.002267257999847061,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006278340010794636,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0016394239987675974,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0016394239987675974
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.03635776800001622,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006626430003962014,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0004486289999476867,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004486289999476867
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.03332802699969761,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.03332802699969761
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0019184689999747206,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.000384164001843601,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0015343049981311196,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0015343049981311196
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1079.5981461610172,
+                                                    "count": 90937,
+                                                    "is_parallel": true,
+                                                    "self": 50.25786231405209,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 25.903580183053236,
+                                                            "count": 90937,
+                                                            "is_parallel": true,
+                                                            "self": 25.903580183053236
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 841.3179651519408,
+                                                            "count": 90937,
+                                                            "is_parallel": true,
+                                                            "self": 841.3179651519408
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 162.11873851197106,
+                                                            "count": 90937,
+                                                            "is_parallel": true,
+                                                            "self": 30.02490029970477,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 132.0938382122663,
+                                                                    "count": 909370,
+                                                                    "is_parallel": true,
+                                                                    "self": 132.0938382122663
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.00027178799973626155,
+                    "count": 1,
+                    "self": 0.00027178799973626155,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 2377.365304975332,
+                                    "count": 2988401,
+                                    "is_parallel": true,
+                                    "self": 63.038587222246406,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 1284.1027207450825,
+                                            "count": 2988401,
+                                            "is_parallel": true,
+                                            "self": 1278.671615995086,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 5.431104749996393,
+                                                    "count": 20,
+                                                    "is_parallel": true,
+                                                    "self": 5.431104749996393
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 1030.2239970080032,
+                                            "count": 454,
+                                            "is_parallel": true,
+                                            "self": 311.0489395849968,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 719.1750574230064,
+                                                    "count": 30868,
+                                                    "is_parallel": true,
+                                                    "self": 719.1750574230064
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.1579831409999315,
+                    "count": 1,
+                    "self": 0.0033865980003611185,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.15459654299957037,
+                            "count": 1,
+                            "self": 0.15459654299957037
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 599936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-599936.onnx",
+                "reward": 29.363636363636363,
+                "creation_time": 1711888306.1372657,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-599936.pt"
+                ]
+            },
+            {
+                "steps": 649960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-649960.onnx",
+                "reward": 28.727272727272727,
+                "creation_time": 1711888426.465772,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-649960.pt"
+                ]
+            },
+            {
+                "steps": 699984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-699984.onnx",
+                "reward": 29.09090909090909,
+                "creation_time": 1711888545.525095,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-699984.pt"
+                ]
+            },
+            {
+                "steps": 749984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-749984.onnx",
+                "reward": 28.454545454545453,
+                "creation_time": 1711888664.160747,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-749984.pt"
+                ]
+            },
+            {
+                "steps": 799944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-799944.onnx",
+                "reward": 28.454545454545453,
+                "creation_time": 1711888783.5290794,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-799944.pt"
+                ]
+            },
+            {
+                "steps": 849968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-849968.onnx",
+                "reward": 29.636363636363637,
+                "creation_time": 1711888903.850849,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-849968.pt"
+                ]
+            },
+            {
+                "steps": 899992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-899992.onnx",
+                "reward": 29.272727272727273,
+                "creation_time": 1711889023.9402714,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-899992.pt"
+                ]
+            },
+            {
+                "steps": 949992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-949992.onnx",
+                "reward": 29.181818181818183,
+                "creation_time": 1711889144.6242595,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-949992.pt"
+                ]
+            },
+            {
+                "steps": 999952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-999952.onnx",
+                "reward": 31.0,
+                "creation_time": 1711889265.5921113,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-999952.pt"
+                ]
+            },
+            {
+                "steps": 1000208,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000208.onnx",
+                "reward": 31.0,
+                "creation_time": 1711889265.7987838,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000208.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 1000208,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 31.0,
+            "creation_time": 1711889265.7987838,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000208.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.2.1+cu121"
+    }
+}