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: mesa44/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:c9e3df6fe0087c4e3eda04028b086bd24c0eea8cf65846b5053a5aff1d65c35d
+size 650646

SnowballTarget/SnowballTarget-1000208.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9e3df6fe0087c4e3eda04028b086bd24c0eea8cf65846b5053a5aff1d65c35d
+size 650646

SnowballTarget/SnowballTarget-1000208.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d231d8114cc61ac25a9b733525ee90264e93e117e16c98db48142a63309d883f
+size 3850214

SnowballTarget/SnowballTarget-599936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57087c6ed6a973779d91e76950f047987c8b317f187fae0a6951670d49c65b78
+size 650646

SnowballTarget/SnowballTarget-599936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff511d1e88377d7b58140915e35f58a9731bb7b13249529a8381669774a36753
+size 3850075

SnowballTarget/SnowballTarget-649960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ecb73a3a679c66c29b4c70ac5af52d1976eed91afa53279577945141638a14e
+size 650646

SnowballTarget/SnowballTarget-649960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fc2134f4221b682b2378abfe5de90eec77be41143513de48754e95ce63e775a
+size 3850075

SnowballTarget/SnowballTarget-699984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:593e8abc3f46d46635439fde90107eea803a3f61c3c6d4000cd13e3af30c6ed2
+size 650646

SnowballTarget/SnowballTarget-699984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dcc3722f0a959288cfae47eaba6d200c407b94105d4ee0f77feceace725969b
+size 3850075

SnowballTarget/SnowballTarget-749984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4a257e9a5ad12bd459f1eb0fe8fbdb51a11101cd340b7e79e6424d556f584da
+size 650646

SnowballTarget/SnowballTarget-749984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00eaf60a58a632bd0959113d702eeff4dd74cba12258706a7bf0511d32980986
+size 3850075

SnowballTarget/SnowballTarget-799944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41c822fb50184a3f0781b56df28db704c9b4c3367146e59cef9e33f01c7245ec
+size 650646

SnowballTarget/SnowballTarget-799944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:504ca548bc4071338edf56e13f784fee14fc23d71a47b86ce35d7925ac75b02a
+size 3850075

SnowballTarget/SnowballTarget-849968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a8c07a91368e107a909678f333e950599f8cc2ecaec51f11778f49f0ccdbf81
+size 650646

SnowballTarget/SnowballTarget-849968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbc62907fb7ca5d65eea60c516c230aa3a0d31d9da19d9ce0d889eb0712e56be
+size 3850075

SnowballTarget/SnowballTarget-899992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afebccdf9d69d1be4aa0841b9f6b1e458cc45c326dace3101152363c2aca5d62
+size 650646

SnowballTarget/SnowballTarget-899992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7053d11fb32b933bcca728591a08ccac73b55e7140bc0b1f57c2c38defa9745
+size 3850075

SnowballTarget/SnowballTarget-949992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21281f179643864687fecbb44359bab9fdd9576e8d1a0a81ba2f07c6d28e8f17
+size 650646

SnowballTarget/SnowballTarget-949992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a3ade096d2ffbdfef49faf009c6788dc70457217423ec634b596ae995ab1a65
+size 3850075

SnowballTarget/SnowballTarget-999952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9e3df6fe0087c4e3eda04028b086bd24c0eea8cf65846b5053a5aff1d65c35d
+size 650646

SnowballTarget/SnowballTarget-999952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cccb981977808c56a65ee137aff5a7a094be68ab4ffd9d59de0a4a6bf0a060e
+size 3850075

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c39463a9c8a8770fd6f4a1b399c70ef91434f0fa3cb10b7ca46e856bb1155c18
+size 3849250

SnowballTarget/events.out.tfevents.1708246880.fc99a197a821.1802.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bb1ec0f41c305272bc40e3e9561c6398dae9dbe235f4a7fbdb71c2de59148d3
+size 104559

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 512, "buffer_size": 4096, "learning_rate": 0.003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 64, "summary_freq": 10000, "threaded": 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: 512
+      buffer_size: 4096
+      learning_rate: 0.003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 50000
+    network_settings:
+      normalize: false
+      hidden_units: 256
+      num_layers: 2
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+    init_path: null
+    keep_checkpoints: 10
+    even_checkpoints: false
+    max_steps: 1000000
+    time_horizon: 64
+    summary_freq: 10000
+    threaded: 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  0.124 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: 0.892397 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]: 26826 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 40
+    [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]: 11553 frames, [8.0 MB-16.0 MB]: 15728 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 2
+      Peak Allocated memory 14.5 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 27281 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.7 MB
+      Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 26566 frames, [64.0 KB-128.0 KB]: 715 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]: 27281 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]: 27281 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]: 27280 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]: 27281 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]: 27281 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": 0.7879202365875244,
+            "min": 0.786651074886322,
+            "max": 2.8786001205444336,
+            "count": 100
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 7514.39501953125,
+            "min": 7514.39501953125,
+            "max": 29543.07421875,
+            "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": 14.509793281555176,
+            "min": 0.052285898476839066,
+            "max": 14.530828475952148,
+            "count": 100
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2829.40966796875,
+            "min": 10.143464088439941,
+            "max": 2970.48876953125,
+            "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.Environment.CumulativeReward.mean": {
+            "value": 28.266666666666666,
+            "min": 2.840909090909091,
+            "max": 28.763636363636362,
+            "count": 100
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1272.0,
+            "min": 125.0,
+            "max": 1582.0,
+            "count": 100
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 28.266666666666666,
+            "min": 2.840909090909091,
+            "max": 28.763636363636362,
+            "count": 100
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1272.0,
+            "min": 125.0,
+            "max": 1582.0,
+            "count": 100
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.0348583965630193,
+            "min": 0.02223999684671677,
+            "max": 0.04416433579172008,
+            "count": 100
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.0697167931260386,
+            "min": 0.04447999369343354,
+            "max": 0.12209505223048231,
+            "count": 100
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.14338716150571904,
+            "min": 0.12423156294971704,
+            "max": 0.34505327604711056,
+            "count": 100
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.28677432301143807,
+            "min": 0.2484631258994341,
+            "max": 0.9872858139375846,
+            "count": 100
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 1.0464099651199974e-05,
+            "min": 1.0464099651199974e-05,
+            "max": 0.0029804640006512,
+            "count": 100
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 2.092819930239995e-05,
+            "min": 2.092819930239995e-05,
+            "max": 0.008683992010533602,
+            "count": 100
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10034880000000002,
+            "min": 0.10034880000000002,
+            "max": 0.1993488,
+            "count": 100
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.20069760000000003,
+            "min": 0.20069760000000003,
+            "max": 0.5894664000000001,
+            "count": 100
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 2.7405119999999957e-05,
+            "min": 2.7405119999999957e-05,
+            "max": 0.00496750512,
+            "count": 100
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 5.4810239999999914e-05,
+            "min": 5.4810239999999914e-05,
+            "max": 0.01447437336,
+            "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": "1708246879",
+        "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": "2.2.0+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1708249064"
+    },
+    "total": 2185.0026652879997,
+    "count": 1,
+    "self": 0.5593132280000646,
+    "children": {
+        "run_training.setup": {
+            "total": 0.05087015499998415,
+            "count": 1,
+            "self": 0.05087015499998415
+        },
+        "TrainerController.start_learning": {
+            "total": 2184.392481905,
+            "count": 1,
+            "self": 2.8296258870118436,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 3.4611041020000357,
+                    "count": 1,
+                    "self": 3.4611041020000357
+                },
+                "TrainerController.advance": {
+                    "total": 2177.998655088988,
+                    "count": 90936,
+                    "self": 1.3659820560360458,
+                    "children": {
+                        "env_step": {
+                            "total": 2176.632673032952,
+                            "count": 90936,
+                            "self": 1381.6864568318629,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 793.4833290320591,
+                                    "count": 90936,
+                                    "self": 7.470601420104117,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 786.012727611955,
+                                            "count": 90936,
+                                            "self": 786.012727611955
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 1.4628871690299547,
+                                    "count": 90936,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 2178.8881813100047,
+                                            "count": 90936,
+                                            "is_parallel": true,
+                                            "self": 1033.063766807066,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.006693552000001546,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.004132064000089031,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.002561487999912515,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.002561487999912515
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.04525442600004226,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0007054420000827122,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0005453719999763962,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0005453719999763962
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.0418211389999783,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0418211389999783
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0021824730000048476,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004194029999666782,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0017630700000381694,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0017630700000381694
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1145.8244145029387,
+                                                    "count": 90935,
+                                                    "is_parallel": true,
+                                                    "self": 55.586330102000375,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 28.834432134987367,
+                                                            "count": 90935,
+                                                            "is_parallel": true,
+                                                            "self": 28.834432134987367
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 879.1323398199252,
+                                                            "count": 90935,
+                                                            "is_parallel": true,
+                                                            "self": 879.1323398199252
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 182.2713124460259,
+                                                            "count": 90935,
+                                                            "is_parallel": true,
+                                                            "self": 33.14124962812127,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 149.13006281790462,
+                                                                    "count": 909350,
+                                                                    "is_parallel": true,
+                                                                    "self": 149.13006281790462
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.0002719849999266444,
+                    "count": 1,
+                    "self": 0.0002719849999266444,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 2137.3701267639317,
+                                    "count": 4541164,
+                                    "is_parallel": true,
+                                    "self": 100.80098829724375,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 1542.0362937366895,
+                                            "count": 4541164,
+                                            "is_parallel": true,
+                                            "self": 1538.803203035689,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 3.233090701000606,
+                                                    "count": 20,
+                                                    "is_parallel": true,
+                                                    "self": 3.233090701000606
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 494.5328447299984,
+                                            "count": 227,
+                                            "is_parallel": true,
+                                            "self": 249.2875851749942,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 245.24525955500417,
+                                                    "count": 5448,
+                                                    "is_parallel": true,
+                                                    "self": 245.24525955500417
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.10282484200024555,
+                    "count": 1,
+                    "self": 0.0010113700004694692,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.10181347199977608,
+                            "count": 1,
+                            "self": 0.10181347199977608
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 599936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-599936.onnx",
+                "reward": 28.09090909090909,
+                "creation_time": 1708248199.3031187,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-599936.pt"
+                ]
+            },
+            {
+                "steps": 649960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-649960.onnx",
+                "reward": 27.454545454545453,
+                "creation_time": 1708248306.3820584,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-649960.pt"
+                ]
+            },
+            {
+                "steps": 699984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-699984.onnx",
+                "reward": 27.727272727272727,
+                "creation_time": 1708248415.8886535,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-699984.pt"
+                ]
+            },
+            {
+                "steps": 749984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-749984.onnx",
+                "reward": 27.636363636363637,
+                "creation_time": 1708248523.6707287,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-749984.pt"
+                ]
+            },
+            {
+                "steps": 799944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-799944.onnx",
+                "reward": 28.727272727272727,
+                "creation_time": 1708248631.9244564,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-799944.pt"
+                ]
+            },
+            {
+                "steps": 849968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-849968.onnx",
+                "reward": 27.272727272727273,
+                "creation_time": 1708248740.6107056,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-849968.pt"
+                ]
+            },
+            {
+                "steps": 899992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-899992.onnx",
+                "reward": 29.045454545454547,
+                "creation_time": 1708248847.9406078,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-899992.pt"
+                ]
+            },
+            {
+                "steps": 949992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-949992.onnx",
+                "reward": 28.0,
+                "creation_time": 1708248955.4221933,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-949992.pt"
+                ]
+            },
+            {
+                "steps": 999952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-999952.onnx",
+                "reward": 27.454545454545453,
+                "creation_time": 1708249063.8361607,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-999952.pt"
+                ]
+            },
+            {
+                "steps": 1000208,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000208.onnx",
+                "reward": 27.454545454545453,
+                "creation_time": 1708249063.9817007,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000208.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 1000208,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 27.454545454545453,
+            "creation_time": 1708249063.9817007,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000208.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.2.0+cu121"
+    }
+}