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: PaulTbbr/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 sha256:7ba959c72914330562e8c18a14cadc5a156d2e1a59382a73d23ca9b6a6f69502
+size 2867524

SnowballTarget/SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60f123815e5db3fbc29abeeecd650f0ecf7bdba8770d9b7292dc6937882c5427
+size 2867524

SnowballTarget/SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd94dab312a0decf7bf95b0a8afefd5bf41a68641dffc959ff8c547686e0933a
+size 17129483

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7fc0c0a913c1d8a36ec728c92fbef2c918ea014edb77a88a2ca187050a632a5
+size 2867524

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:771fb089f5b14f712a0199d057e53fc7ae9440beb7effc50efd06cfc6e167dec
+size 17129483

SnowballTarget/SnowballTarget-249880.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:674e2443ecfe3f290fe46577cf1562fe0baafa2d5cd6f66b2ee4517bd6f99f8c
+size 2867524

SnowballTarget/SnowballTarget-249880.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e662e172378b5dc96df2f5f31b2a46e802ff7531906728848c26ee3fd51dcdfb
+size 17129483

SnowballTarget/SnowballTarget-299968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc2242ee0dbaff7fef9fe8fa1d97c984d884e20a2f9fed15b48e566baa6b21bd
+size 2867524

SnowballTarget/SnowballTarget-299968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:338077ae45d4c359126fa9ed614a3b0a0d60f44e87676356e3ada3d97471d358
+size 17129483

SnowballTarget/SnowballTarget-349928.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:043a9f6a1f4ac4e3d912f20185a4ce2eb00b36dc9419c9f99f313099c478dd5d
+size 2867524

SnowballTarget/SnowballTarget-349928.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:330870fe838d1d03c3ce16e9eb6c3be292e01db630da14248cb1d3cd0d94770f
+size 17129483

SnowballTarget/SnowballTarget-399968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d18767dfbe2757dbb474390aed51953bfe66d06ce0d09934becd06809795bbf
+size 2867524

SnowballTarget/SnowballTarget-399968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab9c4dfd809d40bfab5a501f552e88e0ce4b9c040eefa798c395d60137ac03ea
+size 17129483

SnowballTarget/SnowballTarget-449952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61b7129529bf9ac9a1b6245812246269c7962b89e1febff5534bb7319b7cfa94
+size 2867524

SnowballTarget/SnowballTarget-449952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f87dc3075905600d653d16cca34ee728cafb4b2b96202f5461d1323f820192c0
+size 17129483

SnowballTarget/SnowballTarget-499912.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ba959c72914330562e8c18a14cadc5a156d2e1a59382a73d23ca9b6a6f69502
+size 2867524

SnowballTarget/SnowballTarget-499912.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1102d3602d3068dba3be7e3ebad029abf40fb05922158fa67b4f1c7d39673530
+size 17129483

SnowballTarget/SnowballTarget-500808.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ba959c72914330562e8c18a14cadc5a156d2e1a59382a73d23ca9b6a6f69502
+size 2867524

SnowballTarget/SnowballTarget-500808.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8fc0b55e68e77a546ad9a43176e00c85ce2dffd7cbc50961cbf3ffaaf11e30d
+size 17129483

SnowballTarget/SnowballTarget-99896.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf08879180128ce158ea4ca376bada69fe46810d0b606bbe92aa97d783999f42
+size 2867524

SnowballTarget/SnowballTarget-99896.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88363960a22d393cd08f1095d3fcb6d57b798fe075f8aa4b1d21891af4e8d5ff
+size 17129392

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:326aa117bb9c2af94ec99596e150cb97110dd847452d2ed187d3a0b3d05028d4
+size 17128482

SnowballTarget/events.out.tfevents.1711910970.8fd64d7e3e0e.4078.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:399a985afbdaf0bd0cf309989fc5ada29ea8baa6c6fd8f868ad9ecf9392d63fd
+size 48167

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": 512, "num_layers": 3, "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": 500000, "time_horizon": 128, "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": 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: 512
+      num_layers: 3
+      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: 500000
+    time_horizon: 128
+    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: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,262 @@
+Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
+PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
+Unable to load player prefs
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+FMOD initialized on nosound output
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.146 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: 0.886210 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]: 13437 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 48
+    [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]: 10874 frames, [8.0 MB-16.0 MB]: 2791 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 9.7 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 13665 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]: 12042 frames, [64.0 KB-128.0 KB]: 1623 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]: 13665 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]: 13665 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]: 13664 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]: 13665 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]: 13665 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": 0.7855961322784424,
+            "min": 0.7522308826446533,
+            "max": 2.854323387145996,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 8079.85595703125,
+            "min": 6968.009765625,
+            "max": 29582.890625,
+            "count": 50
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 499912.0,
+            "min": 9952.0,
+            "max": 499912.0,
+            "count": 50
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 499912.0,
+            "min": 9952.0,
+            "max": 499912.0,
+            "count": 50
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 13.80102825164795,
+            "min": 0.5273751616477966,
+            "max": 13.889245986938477,
+            "count": 50
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 1393.90380859375,
+            "min": 51.155391693115234,
+            "max": 1420.9559326171875,
+            "count": 50
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 50
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 8756.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 50
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 26.90566037735849,
+            "min": 4.590909090909091,
+            "max": 27.528301886792452,
+            "count": 50
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1426.0,
+            "min": 202.0,
+            "max": 1500.0,
+            "count": 50
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 26.90566037735849,
+            "min": 4.590909090909091,
+            "max": 27.528301886792452,
+            "count": 50
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1426.0,
+            "min": 202.0,
+            "max": 1500.0,
+            "count": 50
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.0706031675779206,
+            "min": 0.05844538613846274,
+            "max": 0.07847299272418204,
+            "count": 50
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.35301583788960295,
+            "min": 0.23378154455385097,
+            "max": 0.3923649636209102,
+            "count": 50
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.162031541121941,
+            "min": 0.15905845062989815,
+            "max": 0.30567985458993446,
+            "count": 50
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.8101577056097049,
+            "min": 0.640297165980526,
+            "max": 1.4484163169182982,
+            "count": 50
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 3.000099000000003e-06,
+            "min": 3.000099000000003e-06,
+            "max": 0.0002967000011,
+            "count": 50
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 1.5000495000000015e-05,
+            "min": 1.5000495000000015e-05,
+            "max": 0.0014538000154,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.101,
+            "min": 0.101,
+            "max": 0.19890000000000002,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.505,
+            "min": 0.41192000000000006,
+            "max": 0.9846000000000001,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 5.9900000000000047e-05,
+            "min": 5.9900000000000047e-05,
+            "max": 0.00494511,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.00029950000000000023,
+            "min": 0.00029950000000000023,
+            "max": 0.024231540000000003,
+            "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": "1711910969",
+        "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",
+        "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": "1711912238"
+    },
+    "total": 1269.331869646,
+    "count": 1,
+    "self": 0.49331525700017664,
+    "children": {
+        "run_training.setup": {
+            "total": 0.09995147799997994,
+            "count": 1,
+            "self": 0.09995147799997994
+        },
+        "TrainerController.start_learning": {
+            "total": 1268.7386029109998,
+            "count": 1,
+            "self": 1.7896298090290657,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 3.61966818399992,
+                    "count": 1,
+                    "self": 3.61966818399992
+                },
+                "TrainerController.advance": {
+                    "total": 1263.136199706971,
+                    "count": 45549,
+                    "self": 0.8693825129778361,
+                    "children": {
+                        "env_step": {
+                            "total": 1262.2668171939931,
+                            "count": 45549,
+                            "self": 799.4751858580075,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 461.89165997797954,
+                                    "count": 45549,
+                                    "self": 4.434828821973724,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 457.4568311560058,
+                                            "count": 45549,
+                                            "self": 457.4568311560058
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.8999713580060416,
+                                    "count": 45549,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 1264.7884437870268,
+                                            "count": 45549,
+                                            "is_parallel": true,
+                                            "self": 604.0081909900478,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.010980506999999307,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0052514710001787535,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.005729035999820553,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.005729035999820553
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.09189107100007732,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0009545119999074814,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00046635200010314293,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00046635200010314293
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.08753799900000558,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.08753799900000558
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0029322080000611095,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0006010200000901023,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0023311879999710072,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0023311879999710072
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 660.7802527969791,
+                                                    "count": 45548,
+                                                    "is_parallel": true,
+                                                    "self": 30.463776162985255,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 15.391914735984756,
+                                                            "count": 45548,
+                                                            "is_parallel": true,
+                                                            "self": 15.391914735984756
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 519.2573805429879,
+                                                            "count": 45548,
+                                                            "is_parallel": true,
+                                                            "self": 519.2573805429879
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 95.66718135502117,
+                                                            "count": 45548,
+                                                            "is_parallel": true,
+                                                            "self": 18.42261674109875,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 77.24456461392242,
+                                                                    "count": 455480,
+                                                                    "is_parallel": true,
+                                                                    "self": 77.24456461392242
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.000772503999996843,
+                    "count": 1,
+                    "self": 0.000772503999996843,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 1250.7491818339215,
+                                    "count": 1519387,
+                                    "is_parallel": true,
+                                    "self": 33.53253266208617,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 561.6681466898335,
+                                            "count": 1519387,
+                                            "is_parallel": true,
+                                            "self": 558.4414686368334,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 3.2266780530001142,
+                                                    "count": 10,
+                                                    "is_parallel": true,
+                                                    "self": 3.2266780530001142
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 655.5485024820019,
+                                            "count": 227,
+                                            "is_parallel": true,
+                                            "self": 156.73636252800816,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 498.8121399539938,
+                                                    "count": 11577,
+                                                    "is_parallel": true,
+                                                    "self": 498.8121399539938
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.1923327069998777,
+                    "count": 1,
+                    "self": 0.0032472439997945912,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.1890854630000831,
+                            "count": 1,
+                            "self": 0.1890854630000831
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 99896,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99896.onnx",
+                "reward": null,
+                "creation_time": 1711911233.1679072,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99896.pt"
+                ]
+            },
+            {
+                "steps": 149984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": null,
+                "creation_time": 1711911362.4402287,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 24.25,
+                "creation_time": 1711911484.4651737,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 249880,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249880.onnx",
+                "reward": null,
+                "creation_time": 1711911607.9752817,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-249880.pt"
+                ]
+            },
+            {
+                "steps": 299968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.onnx",
+                "reward": null,
+                "creation_time": 1711911733.657446,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.pt"
+                ]
+            },
+            {
+                "steps": 349928,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349928.onnx",
+                "reward": null,
+                "creation_time": 1711911861.1791756,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-349928.pt"
+                ]
+            },
+            {
+                "steps": 399968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.onnx",
+                "reward": 26.4,
+                "creation_time": 1711911985.114148,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.pt"
+                ]
+            },
+            {
+                "steps": 449952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.onnx",
+                "reward": null,
+                "creation_time": 1711912110.981319,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.pt"
+                ]
+            },
+            {
+                "steps": 499912,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499912.onnx",
+                "reward": null,
+                "creation_time": 1711912237.9297612,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-499912.pt"
+                ]
+            },
+            {
+                "steps": 500808,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-500808.onnx",
+                "reward": null,
+                "creation_time": 1711912238.2123308,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-500808.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 500808,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": null,
+            "creation_time": 1711912238.2123308,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-500808.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.2.1+cu121"
+    }
+}