Trained SnowballTarget agent upload

README.md

@@ -0,0 +1,31 @@
+
+---
+      tags:
+      - unity-ml-agents
+      - ml-agents
+      - deep-reinforcement-learning
+      - reinforcement-learning
+      - ML-Agents-SnowballTarget
+      library_name: ml-agents
+---
+    
+  # **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://github.com/huggingface/ml-agents#get-started
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+
+
+  ### Resume the training
+  ```
+  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. Go to https://huggingface.co/spaces/unity/ML-Agents-SnowballTarget
+  2. Step 1: Write your model_id: akanametov/MLAgents-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 sha256:739ff54692ec7b93f99eea67d594e09ff0c1892c1d822e753a6da40067fe0f22
+size 645119

SnowballTarget/SnowballTarget-1599976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ac86c2879d04ca977aea96085ed7d93550be2561c320dc4fc4ca18e808203ec
+size 645119

SnowballTarget/SnowballTarget-1599976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:915f9ab49a58c6755c46e78df9758a163c15defbcec428f95a46bd16343a0764
+size 3845312

SnowballTarget/SnowballTarget-1649992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96b19c978b3f6a2f27706cf0d1e886de5875e274833bde74d5a5749d67471de9
+size 645119

SnowballTarget/SnowballTarget-1649992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee3cecfe3e716b06a76166f5c7443a9ecae20912c30b5a140fd203ffdf4b6713
+size 3845312

SnowballTarget/SnowballTarget-1699936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32e3d65e352c5780bd6a280dcd1e3169610a8d23dc0102e9af6f13f97718dba2
+size 645119

SnowballTarget/SnowballTarget-1699936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eaa8b2b13474e73835f39fe7ae5e8e7da4d80cd4028b3c3894bb9c196a7f6f7
+size 3845312

SnowballTarget/SnowballTarget-1749960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:244ae7dff7cf19c268837b7d238696332e140acaf7e6139acab552897484616e
+size 645119

SnowballTarget/SnowballTarget-1749960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d19490715d664d5395b24e68f45bf1a080334e7c4d2378a1e9b8fef6aa513b42
+size 3845312

SnowballTarget/SnowballTarget-1799984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:429e0409e86db0efd1a334735763a18b48b8f4d1857139f21457529e37881bcb
+size 645119

SnowballTarget/SnowballTarget-1799984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5d4681408ff7c98838d9f715bec1feea12b7d8c265c442e9d6d358ef0a91a78
+size 3845312

SnowballTarget/SnowballTarget-1849984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:334cda1e57d06c9cc9ab86e69fab699e4d16cc42b7968463b73909d697223042
+size 645119

SnowballTarget/SnowballTarget-1849984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45eed40047b25927ab37499ab25de4e42148728a1748b316e9e68a0f0c3995a2
+size 3845312

SnowballTarget/SnowballTarget-1899944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53064e665e7f9dbd16652f0aa40fe46d3449de0285bb2d04c20939fcc67b566f
+size 645119

SnowballTarget/SnowballTarget-1899944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65a54954ce9fbcdc878dfc1625c3267d49e267630ca208afc419a16dfb57a52a
+size 3845312

SnowballTarget/SnowballTarget-1949968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:283b0c7fe3c329cc5c8c1601a74135d6db4d3ad62ead04c9f2df11e8740412ea
+size 645119

SnowballTarget/SnowballTarget-1949968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b0fdc87a9b3b4b3f393d2f2ae852d5c794f936919c0e7feddea108b8dff501e
+size 3845312

SnowballTarget/SnowballTarget-1999992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:739ff54692ec7b93f99eea67d594e09ff0c1892c1d822e753a6da40067fe0f22
+size 645119

SnowballTarget/SnowballTarget-1999992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:963b324ec1e70cecc437d8f91059a122769d1eab993f646aa7e891a50d972020
+size 3845312

SnowballTarget/SnowballTarget-2000376.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:739ff54692ec7b93f99eea67d594e09ff0c1892c1d822e753a6da40067fe0f22
+size 645119

SnowballTarget/SnowballTarget-2000376.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cce7ac1220aae4c4e69fd041bc598f83b7f4b0430eae54bac44fe69a67b4deb6
+size 3845312

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cce7ac1220aae4c4e69fd041bc598f83b7f4b0430eae54bac44fe69a67b4deb6
+size 3845312

SnowballTarget/events.out.tfevents.1673457182.4c77d8001b8d.3516.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:165ad210246e69e1ccac740b0ee21cf8987d88a54e4ca25794f27ea1e5819e88
+size 170238

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, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 50000, "max_steps": 2000000, "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, "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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,75 @@
+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
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    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
+    checkpoint_interval: 50000
+    max_steps: 2000000
+    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
+  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
+environment_parameters: null
+checkpoint_settings:
+  run_id: SnowballTarget
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,262 @@
+Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
+PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
+Unable to load player prefs
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+ALSA lib confmisc.c:767:(parse_card) cannot find card '0'
+ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
+ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
+ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5007:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2495:(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:767:(parse_card) cannot find card '0'
+ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
+ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
+ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5007:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2495:(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  0.073 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: 0.592268 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 0.9 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 13067 frames, [8.0 MB-16.0 MB]: 29887 frames, [16.0 MB-32.0 MB]: 11608 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 2
+      Peak Allocated memory 24.1 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 17.8 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 0.9 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 52870 frames, [64.0 KB-128.0 KB]: 1692 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 67.3 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 0.9 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 0.9 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 +1,384 @@
+{
+    "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 0.6842654943466187,
+            "min": 0.6585708856582642,
+            "max": 2.8669607639312744,
+            "count": 200
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 7045.197265625,
+            "min": 6266.3017578125,
+            "max": 29329.0078125,
+            "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": 14.316854476928711,
+            "min": 0.5071741938591003,
+            "max": 14.503100395202637,
+            "count": 200
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2934.955078125,
+            "min": 98.39179229736328,
+            "max": 2966.3935546875,
+            "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": 0.06498781699877273,
+            "min": 0.059435700111470056,
+            "max": 0.07974589565419592,
+            "count": 200
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.32493908499386365,
+            "min": 0.24175110601537003,
+            "max": 0.3987294782709796,
+            "count": 200
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.16084062839839972,
+            "min": 0.13000560533620564,
+            "max": 0.2675454196392321,
+            "count": 200
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.8042031419919986,
+            "min": 0.5200224213448226,
+            "max": 1.3377270981961606,
+            "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": 27.818181818181817,
+            "min": 3.909090909090909,
+            "max": 28.40909090909091,
+            "count": 200
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1530.0,
+            "min": 172.0,
+            "max": 1560.0,
+            "count": 200
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 27.818181818181817,
+            "min": 3.909090909090909,
+            "max": 28.40909090909091,
+            "count": 200
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1530.0,
+            "min": 172.0,
+            "max": 1560.0,
+            "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": "1673457178",
+        "python_version": "3.8.16 (default, Dec  7 2022, 01:12:13) \n[GCC 7.5.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget --no-graphics",
+        "mlagents_version": "0.29.0.dev0",
+        "mlagents_envs_version": "0.29.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.8.1+cu102",
+        "numpy_version": "1.21.6",
+        "end_time_seconds": "1673461222"
+    },
+    "total": 4044.071929865,
+    "count": 1,
+    "self": 0.3886715559997356,
+    "children": {
+        "run_training.setup": {
+            "total": 0.1093614679999746,
+            "count": 1,
+            "self": 0.1093614679999746
+        },
+        "TrainerController.start_learning": {
+            "total": 4043.5738968410005,
+            "count": 1,
+            "self": 4.748366612919654,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 7.472251443999994,
+                    "count": 1,
+                    "self": 7.472251443999994
+                },
+                "TrainerController.advance": {
+                    "total": 4031.23671099208,
+                    "count": 181873,
+                    "self": 2.376114061205044,
+                    "children": {
+                        "env_step": {
+                            "total": 4028.860596930875,
+                            "count": 181873,
+                            "self": 2613.810338152799,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 1412.5374822040235,
+                                    "count": 181873,
+                                    "self": 13.594108594963018,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 1398.9433736090605,
+                                            "count": 181873,
+                                            "self": 313.5508216142739,
+                                            "children": {
+                                                "TorchPolicy.sample_actions": {
+                                                    "total": 1085.3925519947866,
+                                                    "count": 181873,
+                                                    "self": 1085.3925519947866
+                                                }
+                                            }
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 2.512776574052509,
+                                    "count": 181873,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 4032.2127861501162,
+                                            "count": 181873,
+                                            "is_parallel": true,
+                                            "self": 1932.6208630251517,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.006449565000025359,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.003821614000230511,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.002627950999794848,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.002627950999794848
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.031784923000031995,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0003347200000689554,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00022066299993639404,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00022066299993639404
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.029510478000020157,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.029510478000020157
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0017190620000064882,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004088260000116861,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0013102359999948021,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0013102359999948021
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 2099.5919231249645,
+                                                    "count": 181872,
+                                                    "is_parallel": true,
+                                                    "self": 81.62233324518593,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 47.67572262986869,
+                                                            "count": 181872,
+                                                            "is_parallel": true,
+                                                            "self": 47.67572262986869
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1678.1447378770172,
+                                                            "count": 181872,
+                                                            "is_parallel": true,
+                                                            "self": 1678.1447378770172
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 292.14912937289273,
+                                                            "count": 181872,
+                                                            "is_parallel": true,
+                                                            "self": 61.20169289411672,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 230.947436478776,
+                                                                    "count": 1818720,
+                                                                    "is_parallel": true,
+                                                                    "self": 230.947436478776
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 5.4927000746829435e-05,
+                    "count": 1,
+                    "self": 5.4927000746829435e-05,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 4004.529954632943,
+                                    "count": 3197374,
+                                    "is_parallel": true,
+                                    "self": 81.67191644184959,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 2277.4287665630904,
+                                            "count": 3197374,
+                                            "is_parallel": true,
+                                            "self": 2270.31834149909,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 7.11042506400031,
+                                                    "count": 40,
+                                                    "is_parallel": true,
+                                                    "self": 7.11042506400031
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 1645.4292716280029,
+                                            "count": 909,
+                                            "is_parallel": true,
+                                            "self": 442.0205589010227,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 1203.4087127269802,
+                                                    "count": 46353,
+                                                    "is_parallel": true,
+                                                    "self": 1203.4087127269802
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.11651286500000424,
+                    "count": 1,
+                    "self": 0.0008272420000139391,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.1156856229999903,
+                            "count": 1,
+                            "self": 0.1156856229999903
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 1599976,
+                "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-1599976.onnx",
+                "reward": 27.636363636363637,
+                "creation_time": 1673460420.7619326,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget/SnowballTarget/SnowballTarget-1599976.pt"
+                ]
+            },
+            {
+                "steps": 1649992,
+                "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-1649992.onnx",
+                "reward": 27.0,
+                "creation_time": 1673460521.0670166,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget/SnowballTarget/SnowballTarget-1649992.pt"
+                ]
+            },
+            {
+                "steps": 1699936,
+                "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-1699936.onnx",
+                "reward": 28.545454545454547,
+                "creation_time": 1673460620.901718,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget/SnowballTarget/SnowballTarget-1699936.pt"
+                ]
+            },
+            {
+                "steps": 1749960,
+                "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-1749960.onnx",
+                "reward": 27.545454545454547,
+                "creation_time": 1673460720.4386053,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget/SnowballTarget/SnowballTarget-1749960.pt"
+                ]
+            },
+            {
+                "steps": 1799984,
+                "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-1799984.onnx",
+                "reward": 28.0,
+                "creation_time": 1673460821.459175,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget/SnowballTarget/SnowballTarget-1799984.pt"
+                ]
+            },
+            {
+                "steps": 1849984,
+                "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-1849984.onnx",
+                "reward": 28.0,
+                "creation_time": 1673460919.4777796,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget/SnowballTarget/SnowballTarget-1849984.pt"
+                ]
+            },
+            {
+                "steps": 1899944,
+                "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-1899944.onnx",
+                "reward": 28.545454545454547,
+                "creation_time": 1673461019.5352297,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget/SnowballTarget/SnowballTarget-1899944.pt"
+                ]
+            },
+            {
+                "steps": 1949968,
+                "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-1949968.onnx",
+                "reward": 27.818181818181817,
+                "creation_time": 1673461122.6545086,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget/SnowballTarget/SnowballTarget-1949968.pt"
+                ]
+            },
+            {
+                "steps": 1999992,
+                "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-1999992.onnx",
+                "reward": 27.454545454545453,
+                "creation_time": 1673461221.996438,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget/SnowballTarget/SnowballTarget-1999992.pt"
+                ]
+            },
+            {
+                "steps": 2000376,
+                "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-2000376.onnx",
+                "reward": 27.454545454545453,
+                "creation_time": 1673461222.161324,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget/SnowballTarget/SnowballTarget-2000376.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 2000376,
+            "file_path": "results/SnowballTarget/SnowballTarget.onnx",
+            "reward": 27.454545454545453,
+            "creation_time": 1673461222.161324,
+            "auxillary_file_paths": [
+                "results/SnowballTarget/SnowballTarget/SnowballTarget-2000376.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.29.0.dev0",
+        "torch_version": "1.8.1+cu102"
+    }
+}