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: sylvainlapeyrade/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 sha256:55bf53d9611250f0229f6a6196f2f60bc013ae7e49a1a541c369d4e2f8cb0ba7
+size 650646

SnowballTarget/SnowballTarget-1000120.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55bf53d9611250f0229f6a6196f2f60bc013ae7e49a1a541c369d4e2f8cb0ba7
+size 650646

SnowballTarget/SnowballTarget-1000120.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:694e7ddde8ec95841a944bc0c6a01dd1127be53eb17f6de405ae50d465845e53
+size 3850214

SnowballTarget/SnowballTarget-599976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7d2d9769c55d813b064e5f8ad1c2b12bd64bdc872e0369184f54ab32f093151
+size 650646

SnowballTarget/SnowballTarget-599976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b866af049a197c34058643aae620f3408e87d14556f2196ad48073e69263fdc
+size 3850075

SnowballTarget/SnowballTarget-649936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91e95e0a16fabe641b706d64c90642c87e19c0865072c41b9dcc090ad749fc16
+size 650646

SnowballTarget/SnowballTarget-649936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b530845c91b5c06db50c36a3aea55839ba9402b79ff55dc86b3ec393c723a83b
+size 3850075

SnowballTarget/SnowballTarget-699936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54b0db86fef5fd58a355c76ad2e10bd2c603cfeff624e00a28533da983d3d6bc
+size 650646

SnowballTarget/SnowballTarget-699936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc124cf25404e73832571caeebbeb448c66ff67ff52f50a735326e5490705c45
+size 3850075

SnowballTarget/SnowballTarget-749960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7854c590d995be2933e5eddd9227f5ae151b4faf5a0a9a867bc7c27ac85ca7d1
+size 650646

SnowballTarget/SnowballTarget-749960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6d92fd4eb4ad7ad0ebee6deda092f0cb4788004af8e5cddb6bb95cb8517ad25
+size 3850075

SnowballTarget/SnowballTarget-799984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b78fb732b7bd6c0647f61ced36369c99bbc4200d1c181b8606770bc8fbe040ae
+size 650646

SnowballTarget/SnowballTarget-799984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eda179516093d2b2914b4213c192f771f7c1436bcc60bd679bb002d940d782ec
+size 3850075

SnowballTarget/SnowballTarget-849944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94890bafedb956032ece40c88fd079d52be253053f88bae1909585c80c9862b2
+size 650646

SnowballTarget/SnowballTarget-849944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e9eef2307832c8a8a00cfb12d730072bfa60ff61d7f0c9da0a3029551957907
+size 3850075

SnowballTarget/SnowballTarget-899944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e22f756960223d5e4cb47f7f01248ed3e4cd502d621d1a541ce76228d1f23774
+size 650646

SnowballTarget/SnowballTarget-899944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96f584558038a117514943b3ccaf2dde1cac3989a9e59b6f16fae7ee756549dc
+size 3850075

SnowballTarget/SnowballTarget-949968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46db2129245168657f6585a3a4ffc76e19ccd2b9969e1718fdcbd95de0f4574e
+size 650646

SnowballTarget/SnowballTarget-949968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7f114829170235a7bec76bc04a6dbc805142be2089c862cbee27625ffc4038e
+size 3850075

SnowballTarget/SnowballTarget-999992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55bf53d9611250f0229f6a6196f2f60bc013ae7e49a1a541c369d4e2f8cb0ba7
+size 650646

SnowballTarget/SnowballTarget-999992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe970b76f6d05087b69a2c5c725225993b207c41349de66a8920f419116dee85
+size 3850075

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c1edb6dd23f62784c61f500da624eae31ff1f58ca67387353d80654eec2aa9f
+size 3849250

SnowballTarget/events.out.tfevents.1744793267.d998b483b879.2788.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d619cc4a15171c81c9c8fd8a3c328cb0491d55b2ff08fe53847140fdd2a65de
+size 23975

SnowballTarget/events.out.tfevents.1744793915.d998b483b879.5608.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ead105ee374cc90d21f14eff71868a3e348ac86da5522e9859d0f9378a831da8
+size 25807

SnowballTarget/events.out.tfevents.1744794717.d998b483b879.9025.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:533bf70b08256a1ce59676a1d6ee59af70a28852bc7f3e50f0752435d2851a7d
+size 41909

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": 1000000, "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": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,79 @@
+default_settings: null
+behaviors:
+  SnowballTarget:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 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: 1000000
+    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: true
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,259 @@
+Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+FMOD initialized on nosound output
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.084 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: 0.675293 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]: 13412 frames, [16.0 KB-32.0 KB]: 227 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 37
+    [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]: 12462 frames, [8.0 MB-16.0 MB]: 1178 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 9.6 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 13640 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]: 13373 frames, [64.0 KB-128.0 KB]: 267 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 66.0 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 13640 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]: 13640 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]: 13639 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]: 13640 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]: 13640 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.7 KB
+      Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -0,0 +1,362 @@
+{
+    "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 0.43655845522880554,
+            "min": 0.43655845522880554,
+            "max": 0.661785900592804,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 4187.46875,
+            "min": 4187.46875,
+            "max": 6686.52392578125,
+            "count": 50
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 999992.0,
+            "min": 509968.0,
+            "max": 999992.0,
+            "count": 50
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 999992.0,
+            "min": 509968.0,
+            "max": 999992.0,
+            "count": 50
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 13.855216026306152,
+            "min": 13.41816234588623,
+            "max": 14.054774284362793,
+            "count": 50
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2840.3193359375,
+            "min": 2629.556640625,
+            "max": 2872.60791015625,
+            "count": 50
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06810875531838403,
+            "min": 0.060986768038014366,
+            "max": 0.07725972314576354,
+            "count": 50
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.34054377659192014,
+            "min": 0.24394707215205746,
+            "max": 0.3862986157288177,
+            "count": 50
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.15498749257302752,
+            "min": 0.14771897576603235,
+            "max": 0.19801216610415165,
+            "count": 50
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.7749374628651376,
+            "min": 0.5979825277246681,
+            "max": 0.9198311952983632,
+            "count": 50
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 1.521699492799996e-06,
+            "min": 1.521699492799996e-06,
+            "max": 0.0001483716505428,
+            "count": 50
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 7.60849746399998e-06,
+            "min": 7.60849746399998e-06,
+            "max": 0.0007270082576640001,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10050719999999999,
+            "min": 0.10050719999999999,
+            "max": 0.1494572,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.502536,
+            "min": 0.40598880000000004,
+            "max": 0.7423360000000001,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 3.530927999999995e-05,
+            "min": 3.530927999999995e-05,
+            "max": 0.0024779142800000005,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.00017654639999999973,
+            "min": 0.00017654639999999973,
+            "max": 0.0121425664,
+            "count": 50
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 50
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 10945.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 50
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 27.527272727272727,
+            "min": 25.914893617021278,
+            "max": 27.654545454545456,
+            "count": 50
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1514.0,
+            "min": 1155.0,
+            "max": 1521.0,
+            "count": 50
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 27.527272727272727,
+            "min": 25.914893617021278,
+            "max": 27.654545454545456,
+            "count": 50
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1514.0,
+            "min": 1155.0,
+            "max": 1521.0,
+            "count": 50
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 50
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 50
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1744794717",
+        "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.6.0+cu124",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1744795774"
+    },
+    "total": 1057.707813351,
+    "count": 1,
+    "self": 0.43159520499966675,
+    "children": {
+        "run_training.setup": {
+            "total": 0.020902878000015335,
+            "count": 1,
+            "self": 0.020902878000015335
+        },
+        "TrainerController.start_learning": {
+            "total": 1057.2553152680002,
+            "count": 1,
+            "self": 0.9120429370655074,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.115488909000078,
+                    "count": 1,
+                    "self": 2.115488909000078
+                },
+                "TrainerController.advance": {
+                    "total": 1054.1408575029348,
+                    "count": 45464,
+                    "self": 0.9293232449681454,
+                    "children": {
+                        "env_step": {
+                            "total": 743.9897518249591,
+                            "count": 45464,
+                            "self": 568.0694966199433,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 175.3758045239931,
+                                    "count": 45464,
+                                    "self": 3.1137454590088964,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 172.26205906498421,
+                                            "count": 45464,
+                                            "self": 172.26205906498421
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.5444506810226812,
+                                    "count": 45464,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 1053.9592545540154,
+                                            "count": 45464,
+                                            "is_parallel": true,
+                                            "self": 555.3718577949885,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0027785459999449813,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0007460490003268205,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0020324969996181608,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0020324969996181608
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.03423868599998059,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005425550002655655,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0003852679999454267,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003852679999454267
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.03154332999997678,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.03154332999997678
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0017675329997928202,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003267340000547847,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0014407989997380355,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0014407989997380355
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 498.5873967590269,
+                                                    "count": 45463,
+                                                    "is_parallel": true,
+                                                    "self": 23.904769074012847,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 13.193737811954861,
+                                                            "count": 45463,
+                                                            "is_parallel": true,
+                                                            "self": 13.193737811954861
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 385.21112384109597,
+                                                            "count": 45463,
+                                                            "is_parallel": true,
+                                                            "self": 385.21112384109597
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 76.27776603196321,
+                                                            "count": 45463,
+                                                            "is_parallel": true,
+                                                            "self": 13.655244054914874,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 62.622521977048336,
+                                                                    "count": 454630,
+                                                                    "is_parallel": true,
+                                                                    "self": 62.622521977048336
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 309.22178243300755,
+                            "count": 45464,
+                            "self": 1.0819424590056315,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 65.64676395300353,
+                                    "count": 45464,
+                                    "self": 64.64110211400452,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 1.0056618389990035,
+                                            "count": 10,
+                                            "self": 1.0056618389990035
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 242.4930760209984,
+                                    "count": 227,
+                                    "self": 97.07831676199976,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 145.41475925899863,
+                                            "count": 11574,
+                                            "self": 145.41475925899863
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 8.809997780190315e-07,
+                    "count": 1,
+                    "self": 8.809997780190315e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.08692503800011764,
+                    "count": 1,
+                    "self": 0.0011586649998207577,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.08576637300029688,
+                            "count": 1,
+                            "self": 0.08576637300029688
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 599976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-599976.onnx",
+                "reward": 26.454545454545453,
+                "creation_time": 1744794928.0455985,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-599976.pt"
+                ]
+            },
+            {
+                "steps": 649936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-649936.onnx",
+                "reward": 25.545454545454547,
+                "creation_time": 1744795033.7161531,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-649936.pt"
+                ]
+            },
+            {
+                "steps": 699936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-699936.onnx",
+                "reward": 27.727272727272727,
+                "creation_time": 1744795137.4881873,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-699936.pt"
+                ]
+            },
+            {
+                "steps": 749960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-749960.onnx",
+                "reward": 27.09090909090909,
+                "creation_time": 1744795243.9591713,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-749960.pt"
+                ]
+            },
+            {
+                "steps": 799984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-799984.onnx",
+                "reward": 28.0,
+                "creation_time": 1744795350.8248606,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-799984.pt"
+                ]
+            },
+            {
+                "steps": 849944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-849944.onnx",
+                "reward": 27.545454545454547,
+                "creation_time": 1744795458.325921,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-849944.pt"
+                ]
+            },
+            {
+                "steps": 899944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-899944.onnx",
+                "reward": 28.636363636363637,
+                "creation_time": 1744795561.537409,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-899944.pt"
+                ]
+            },
+            {
+                "steps": 949968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-949968.onnx",
+                "reward": 25.454545454545453,
+                "creation_time": 1744795667.8561578,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-949968.pt"
+                ]
+            },
+            {
+                "steps": 999992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-999992.onnx",
+                "reward": 27.545454545454547,
+                "creation_time": 1744795774.274019,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-999992.pt"
+                ]
+            },
+            {
+                "steps": 1000120,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000120.onnx",
+                "reward": 27.545454545454547,
+                "creation_time": 1744795774.3722537,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000120.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 1000120,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 27.545454545454547,
+            "creation_time": 1744795774.3722537,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000120.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.6.0+cu124"
+    }
+}