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: k0T0z/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 sha256:38330c43c8755778746197fce6f65f26aa4f9f0aa46e7176b99df783b8f502df
+size 1178864

SnowballTarget/SnowballTarget-1000208.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38330c43c8755778746197fce6f65f26aa4f9f0aa46e7176b99df783b8f502df
+size 1178864

SnowballTarget/SnowballTarget-1000208.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:082ad2ec2753e894f97a7e12fdf0ece5dd262ba6a24e684ce1a38ec4b3c9946e
+size 7017321

SnowballTarget/SnowballTarget-599936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4db5b1d7112c23011cff36fc2567578bb5961a5545683f674787f2e7e854303
+size 1178864

SnowballTarget/SnowballTarget-599936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55217cb1d4cfb31129132fff28faa9fa53b1630040d90151a76d0c41032ee87a
+size 7017150

SnowballTarget/SnowballTarget-649960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70fba72c92a7673f905321cb962e7093c5d7f5bedd83f10094a38a686341d7c1
+size 1178864

SnowballTarget/SnowballTarget-649960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c4c334716a155a66a5fef5a9e8bdadb1dc72ea2aa375982ef0867e6addd50c
+size 7017150

SnowballTarget/SnowballTarget-699984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fec1056b7fc4406303087c1fc0539b0ac983453ac1e3337d3992eab956e63f77
+size 1178864

SnowballTarget/SnowballTarget-699984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:455b73e51e6561f9846c94832a782a4492882b2514d5b1ab29655baf840ecbe2
+size 7017150

SnowballTarget/SnowballTarget-749984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fdfb92e3d7cb8a0433a5be8142f95dd78c8c7657fe9873e9a4e531a65f9f8ea
+size 1178864

SnowballTarget/SnowballTarget-749984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54280b077e2f91c113d16c8a8cb9a25bc83bd5b3ca5ac663618d8a26c8ae62b1
+size 7017150

SnowballTarget/SnowballTarget-799944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e67a533cc05a5c6fea9d3c76172f202008aea808f7894ab3c74948c21c82de3
+size 1178864

SnowballTarget/SnowballTarget-799944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54fe0eb5d0be1ca443ce993c0ecdf7c5cd2a00b78f5a63b16d4d4555c28e0e26
+size 7017150

SnowballTarget/SnowballTarget-849968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:865af968587a08c5c2adff50a0fcdc705dda21955f0c57e6bd706a4850d94b45
+size 1178864

SnowballTarget/SnowballTarget-849968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c355e61d8de8929b8c893c6782f70c3362de5204d6d8d54bf54b5001fc388b86
+size 7017150

SnowballTarget/SnowballTarget-899992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a21ee5c25d44a18d8ba7bf0b568d3db92ee907ba5a83d9031d6bf5fad96f0bb
+size 1178864

SnowballTarget/SnowballTarget-899992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74522467d59195fb487a2795a815a3d1eea666112268ffd2fd4f178e91425e7b
+size 7017150

SnowballTarget/SnowballTarget-949992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5cd5ca335f6edd404cb0c06ecbc6b6f178f8f7d2a95d7f3ffc09d59e33eb992
+size 1178864

SnowballTarget/SnowballTarget-949992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60aa5bdf9014c459cfbb4d78f8a7b66c25d3719ca9bdcb7d108e125e9852c2c
+size 7017150

SnowballTarget/SnowballTarget-999952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38330c43c8755778746197fce6f65f26aa4f9f0aa46e7176b99df783b8f502df
+size 1178864

SnowballTarget/SnowballTarget-999952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac2975223eb73cb59a2ac05e151113953460b74287bd3105a35c18eb5e6503e8
+size 7017150

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58471929ae582b7c1c4db7dffd8b8303b3b842502f160783e8ec733890d392d5
+size 7015973

SnowballTarget/events.out.tfevents.1705752665.80e242070a31.7250.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8213434bc7fe6fd60914523cae7d4a2a8b629149828d5b1aa726ed2a8e9f6c8e
+size 94314

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0004, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 5, "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": 4, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,79 @@
+default_settings: null
+behaviors:
+  SnowballTarget:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 2048
+      learning_rate: 0.0004
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 5
+      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: 4
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+    init_path: null
+    keep_checkpoints: 10
+    even_checkpoints: false
+    max_steps: 1000000
+    time_horizon: 64
+    summary_freq: 10000
+    threaded: true
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  timeout_wait: 60
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: SnowballTarget1
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: true
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,262 @@
+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  0.153 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: 1.209410 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]: 26830 frames, [16.0 KB-32.0 KB]: 454 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.0 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 198 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 304.0 KB
+      Peak Allocated Bytes 228.9 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 50
+    [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]: 12231 frames, [8.0 MB-16.0 MB]: 15054 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 2
+      Peak Allocated memory 14.4 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 27285 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]: 26500 frames, [64.0 KB-128.0 KB]: 785 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 66.4 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 27285 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]: 27285 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]: 27284 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]: 27285 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]: 27285 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": 0.7093857526779175,
+            "min": 0.68915194272995,
+            "max": 2.86297607421875,
+            "count": 100
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 6757.60888671875,
+            "min": 6595.18408203125,
+            "max": 29382.72265625,
+            "count": 100
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 999952.0,
+            "min": 9952.0,
+            "max": 999952.0,
+            "count": 100
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 999952.0,
+            "min": 9952.0,
+            "max": 999952.0,
+            "count": 100
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 14.376633644104004,
+            "min": 0.451972633600235,
+            "max": 14.548315048217773,
+            "count": 100
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2803.443603515625,
+            "min": 87.68269348144531,
+            "max": 2972.89453125,
+            "count": 100
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 100
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 8756.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 100
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06875585216694162,
+            "min": 0.062443952937182454,
+            "max": 0.07684726449763676,
+            "count": 100
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.2750234086677665,
+            "min": 0.24977581174872981,
+            "max": 0.3653218817642483,
+            "count": 100
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.15356399132048382,
+            "min": 0.12475253410007367,
+            "max": 0.27994405535214084,
+            "count": 100
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.6142559652819353,
+            "min": 0.4990101364002947,
+            "max": 1.3220909725217258,
+            "count": 100
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 1.8352995412000037e-06,
+            "min": 1.8352995412000037e-06,
+            "max": 0.00039783520054120005,
+            "count": 100
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 7.341198164800015e-06,
+            "min": 7.341198164800015e-06,
+            "max": 0.001969376007656,
+            "count": 100
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10045880000000001,
+            "min": 0.10045880000000001,
+            "max": 0.19945880000000002,
+            "count": 100
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.40183520000000006,
+            "min": 0.40183520000000006,
+            "max": 0.9923440000000001,
+            "count": 100
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 3.289412000000005e-05,
+            "min": 3.289412000000005e-05,
+            "max": 0.004972994119999999,
+            "count": 100
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0001315764800000002,
+            "min": 0.0001315764800000002,
+            "max": 0.024617965600000007,
+            "count": 100
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 28.57777777777778,
+            "min": 3.8181818181818183,
+            "max": 28.685185185185187,
+            "count": 100
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1286.0,
+            "min": 168.0,
+            "max": 1577.0,
+            "count": 100
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 28.57777777777778,
+            "min": 3.8181818181818183,
+            "max": 28.685185185185187,
+            "count": 100
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1286.0,
+            "min": 168.0,
+            "max": 1577.0,
+            "count": 100
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 100
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 100
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1705752664",
+        "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.1.2+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1705756998"
+    },
+    "total": 4333.933604594999,
+    "count": 1,
+    "self": 1.072528097999566,
+    "children": {
+        "run_training.setup": {
+            "total": 0.09069979600008082,
+            "count": 1,
+            "self": 0.09069979600008082
+        },
+        "TrainerController.start_learning": {
+            "total": 4332.770376701,
+            "count": 1,
+            "self": 5.283740808882612,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 5.3399123490000875,
+                    "count": 1,
+                    "self": 5.3399123490000875
+                },
+                "TrainerController.advance": {
+                    "total": 4321.922220586117,
+                    "count": 90947,
+                    "self": 2.5106592760012063,
+                    "children": {
+                        "env_step": {
+                            "total": 4319.411561310116,
+                            "count": 90947,
+                            "self": 3541.79149806122,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 775.1228558939604,
+                                    "count": 90947,
+                                    "self": 15.90126287695557,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 759.2215930170048,
+                                            "count": 90947,
+                                            "self": 759.2215930170048
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 2.4972073549354263,
+                                    "count": 90947,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 4320.533252514877,
+                                            "count": 90947,
+                                            "is_parallel": true,
+                                            "self": 2488.0631194779216,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.008673203999933321,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.005435309999938909,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0032378939999944123,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0032378939999944123
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.049348313000109556,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0007979040001373505,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.000487903000021106,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.000487903000021106
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.04545025700008409,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.04545025700008409
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.002612248999867006,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004871229998570925,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0021251260000099137,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0021251260000099137
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1832.4701330369555,
+                                                    "count": 90946,
+                                                    "is_parallel": true,
+                                                    "self": 83.47777124174877,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 43.56783141201163,
+                                                            "count": 90946,
+                                                            "is_parallel": true,
+                                                            "self": 43.56783141201163
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1448.1417905950896,
+                                                            "count": 90946,
+                                                            "is_parallel": true,
+                                                            "self": 1448.1417905950896
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 257.2827397881056,
+                                                            "count": 90946,
+                                                            "is_parallel": true,
+                                                            "self": 52.70407596667155,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 204.57866382143402,
+                                                                    "count": 909460,
+                                                                    "is_parallel": true,
+                                                                    "self": 204.57866382143402
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.00039574000038555823,
+                    "count": 1,
+                    "self": 0.00039574000038555823,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 4280.65498954288,
+                                    "count": 4550358,
+                                    "is_parallel": true,
+                                    "self": 111.46386916851407,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 1839.0748376783724,
+                                            "count": 4550358,
+                                            "is_parallel": true,
+                                            "self": 1832.8501009593717,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 6.224736719000703,
+                                                    "count": 20,
+                                                    "is_parallel": true,
+                                                    "self": 6.224736719000703
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 2330.1162826959935,
+                                            "count": 454,
+                                            "is_parallel": true,
+                                            "self": 539.609026397992,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 1790.5072562980015,
+                                                    "count": 38580,
+                                                    "is_parallel": true,
+                                                    "self": 1790.5072562980015
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.22410721699998248,
+                    "count": 1,
+                    "self": 0.0031709009999758564,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.22093631600000663,
+                            "count": 1,
+                            "self": 0.22093631600000663
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 599936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-599936.onnx",
+                "reward": 28.181818181818183,
+                "creation_time": 1705755267.4242027,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-599936.pt"
+                ]
+            },
+            {
+                "steps": 649960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-649960.onnx",
+                "reward": 28.272727272727273,
+                "creation_time": 1705755483.6092334,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-649960.pt"
+                ]
+            },
+            {
+                "steps": 699984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-699984.onnx",
+                "reward": 27.454545454545453,
+                "creation_time": 1705755701.4246862,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-699984.pt"
+                ]
+            },
+            {
+                "steps": 749984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-749984.onnx",
+                "reward": 28.09090909090909,
+                "creation_time": 1705755915.9256706,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-749984.pt"
+                ]
+            },
+            {
+                "steps": 799944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-799944.onnx",
+                "reward": 28.0,
+                "creation_time": 1705756133.2755141,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-799944.pt"
+                ]
+            },
+            {
+                "steps": 849968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-849968.onnx",
+                "reward": 28.727272727272727,
+                "creation_time": 1705756350.8715725,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-849968.pt"
+                ]
+            },
+            {
+                "steps": 899992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-899992.onnx",
+                "reward": 29.09090909090909,
+                "creation_time": 1705756568.8594472,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-899992.pt"
+                ]
+            },
+            {
+                "steps": 949992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-949992.onnx",
+                "reward": 28.454545454545453,
+                "creation_time": 1705756782.4254787,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-949992.pt"
+                ]
+            },
+            {
+                "steps": 999952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-999952.onnx",
+                "reward": 29.181818181818183,
+                "creation_time": 1705756996.6241066,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-999952.pt"
+                ]
+            },
+            {
+                "steps": 1000208,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000208.onnx",
+                "reward": 29.181818181818183,
+                "creation_time": 1705756996.934045,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000208.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 1000208,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 29.181818181818183,
+            "creation_time": 1705756996.934045,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000208.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.1.2+cu121"
+    }
+}