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: vagi/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:b66b9ddacfafa1fd6ee2eee9d7daa616d8621ba4d26b74ce89badf9298e00377
+size 650646

SnowballTarget/SnowballTarget-1000208.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b66b9ddacfafa1fd6ee2eee9d7daa616d8621ba4d26b74ce89badf9298e00377
+size 650646

SnowballTarget/SnowballTarget-1000208.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8876638ddbe1cf17e1a3a891fff88efaf8cf8311b61bbbc2e2ed5e9266afda99
+size 3849254

SnowballTarget/SnowballTarget-599952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46e43c18710c9cc21f193c9ca0d68869df412517d16395ec00f584f73a829d29
+size 650646

SnowballTarget/SnowballTarget-599952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73d3cbeee168136694e39f3ac3bb3df3670e739b7ea1b2b7810ba02a9ab69d79
+size 3849115

SnowballTarget/SnowballTarget-649896.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:865e2d83bf0b9692cbd2d607198f07f901fba7730429cfe209e8d92c1a54a4ad
+size 650646

SnowballTarget/SnowballTarget-649896.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cb77bf21027c86fc285bdb6022f13b8d194af4175d015507e0625bdfa685b1e
+size 3849115

SnowballTarget/SnowballTarget-699984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4237c40843cadb94dd0bcf91da13f1dbd4515687ac6671a42f762ebf1e7f3124
+size 650646

SnowballTarget/SnowballTarget-699984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41f8ac8ff9bbdbe3fd4176201b4d0226249fe1c18cfe9ce30729bb46613c517f
+size 3849115

SnowballTarget/SnowballTarget-749984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58521359edb93b6100cbb480e1a4a46f58824b48d783c3e39b6b0c90e6e3b163
+size 650646

SnowballTarget/SnowballTarget-749984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5acc5e050364659756ac0b4f82eed341aea4828af9a834084ed61560785d1252
+size 3849115

SnowballTarget/SnowballTarget-799880.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e984df0ca36050aef8e7a251924a4654a6a582def9e4ce89290a5c2c16c9c5c7
+size 650646

SnowballTarget/SnowballTarget-799880.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5620b80d954ef1572bffb43c4b12297ac0909be35330a595b49172a66db6a3a4
+size 3849115

SnowballTarget/SnowballTarget-849968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2184fe87da2abd60a29461cc76f5a6d62a5d14a38b7405f17a5243d5746772a0
+size 650646

SnowballTarget/SnowballTarget-849968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12d30e127ec60855925811ee80f770c072a57b3af9be7bad9d264b2f53783fce
+size 3849115

SnowballTarget/SnowballTarget-899928.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ceb251201990c5ea4e6bbdd668462e412ec3df57a0b9fe2fa1d075e5ad17107
+size 650646

SnowballTarget/SnowballTarget-899928.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:984f577c4c0caa9772301797ae528fe0cf256a858696a3cd804f8c0ab3765129
+size 3849115

SnowballTarget/SnowballTarget-949968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43b5f1095c18e80a8632b3aba3b3ce6ba01b9cd2178c2c0a326df75e111bb0e6
+size 650646

SnowballTarget/SnowballTarget-949968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4713acb3b19cc13b5e36e0743a3cab64888bfae4444409fe94a172fc573728e4
+size 3849115

SnowballTarget/SnowballTarget-999952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b66b9ddacfafa1fd6ee2eee9d7daa616d8621ba4d26b74ce89badf9298e00377
+size 650646

SnowballTarget/SnowballTarget-999952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46ffb41ad3eb0b17f7d1213a514e8048bfcd5d175566eb73183d8895bc600213
+size 3849115

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:618d8bcf27e52cba678f41fbed12e8e05d9ddfe28930f9a5a232c3732c63115d
+size 3848290

SnowballTarget/events.out.tfevents.1731953639.ae86e9d8d77d.2374.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2c7a50c1cd213c3c847e6385f39a108c172c86ff737571f2a9864c471aaa778
+size 109632

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 3e-05, "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": 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: 3.0e-05
+      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: 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  0.131 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: 0.947250 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]: 26841 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 44
+    [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]: 12839 frames, [8.0 MB-16.0 MB]: 14457 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 2
+      Peak Allocated memory 14.3 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 27296 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]: 19753 frames, [64.0 KB-128.0 KB]: 7543 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]: 27296 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]: 27296 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]: 27295 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]: 27296 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]: 27296 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": 1.0228780508041382,
+            "min": 1.0089894533157349,
+            "max": 2.8900256156921387,
+            "count": 100
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 10925.3603515625,
+            "min": 8848.869140625,
+            "max": 31482.693359375,
+            "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": 11.43346881866455,
+            "min": 0.22160707414150238,
+            "max": 11.609136581420898,
+            "count": 100
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 1120.47998046875,
+            "min": 21.495885848999023,
+            "max": 1186.4820556640625,
+            "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": 6766.0,
+            "max": 13134.0,
+            "count": 100
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 23.244444444444444,
+            "min": 2.7954545454545454,
+            "max": 23.244444444444444,
+            "count": 100
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1046.0,
+            "min": 123.0,
+            "max": 1251.0,
+            "count": 100
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 23.244444444444444,
+            "min": 2.7954545454545454,
+            "max": 23.244444444444444,
+            "count": 100
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1046.0,
+            "min": 123.0,
+            "max": 1251.0,
+            "count": 100
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06398107699878933,
+            "min": 0.06061989584557321,
+            "max": 0.07829075186121319,
+            "count": 100
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.3199053849939466,
+            "min": 0.24247958338229283,
+            "max": 0.39145375930606596,
+            "count": 100
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.2128410299777303,
+            "min": 0.12767621359842665,
+            "max": 0.3321091840226276,
+            "count": 100
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 1.0642051498886516,
+            "min": 0.5107048543937066,
+            "max": 1.5261432367756411,
+            "count": 100
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 1.698274342399999e-07,
+            "min": 1.698274342399999e-07,
+            "max": 2.9835000549999995e-05,
+            "count": 100
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 8.491371711999995e-07,
+            "min": 8.491371711999995e-07,
+            "max": 0.00014769000770000002,
+            "count": 100
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10056575999999999,
+            "min": 0.10056575999999999,
+            "max": 0.19945000000000002,
+            "count": 100
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.5028288,
+            "min": 0.40621440000000003,
+            "max": 0.9923000000000001,
+            "count": 100
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 3.823142399999998e-05,
+            "min": 3.823142399999998e-05,
+            "max": 0.004972555,
+            "count": 100
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.00019115711999999989,
+            "min": 0.00019115711999999989,
+            "max": 0.02461577,
+            "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": "1731953638",
+        "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.5.1+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1731956498"
+    },
+    "total": 2860.453697244,
+    "count": 1,
+    "self": 0.7388806459998705,
+    "children": {
+        "run_training.setup": {
+            "total": 0.08470119200001136,
+            "count": 1,
+            "self": 0.08470119200001136
+        },
+        "TrainerController.start_learning": {
+            "total": 2859.630115406,
+            "count": 1,
+            "self": 5.081219978017543,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 7.751238744000034,
+                    "count": 1,
+                    "self": 7.751238744000034
+                },
+                "TrainerController.advance": {
+                    "total": 2846.688965172983,
+                    "count": 90984,
+                    "self": 2.484517048957059,
+                    "children": {
+                        "env_step": {
+                            "total": 2844.204448124026,
+                            "count": 90984,
+                            "self": 2022.305275577124,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 819.4286243739347,
+                                    "count": 90984,
+                                    "self": 14.019601746953526,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 805.4090226269811,
+                                            "count": 90984,
+                                            "self": 805.4090226269811
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 2.4705481729673693,
+                                    "count": 90984,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 2849.3952631419884,
+                                            "count": 90984,
+                                            "is_parallel": true,
+                                            "self": 1216.1327046770268,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0030797959999517843,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0012395549999837385,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0018402409999680458,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0018402409999680458
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.05030902299995432,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0009406859999216977,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0005251699999462289,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0005251699999462289
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.045987514999978885,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.045987514999978885
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0028556520001075114,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0005317250000871354,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.002323927000020376,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.002323927000020376
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1633.2625584649616,
+                                                    "count": 90983,
+                                                    "is_parallel": true,
+                                                    "self": 77.48289895989865,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 37.49257658206227,
+                                                            "count": 90983,
+                                                            "is_parallel": true,
+                                                            "self": 37.49257658206227
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1290.9427687699626,
+                                                            "count": 90983,
+                                                            "is_parallel": true,
+                                                            "self": 1290.9427687699626
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 227.3443141530381,
+                                                            "count": 90983,
+                                                            "is_parallel": true,
+                                                            "self": 45.97291112913979,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 181.37140302389832,
+                                                                    "count": 909830,
+                                                                    "is_parallel": true,
+                                                                    "self": 181.37140302389832
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.0008614979997219052,
+                    "count": 1,
+                    "self": 0.0008614979997219052,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 2844.9068765460206,
+                                    "count": 678885,
+                                    "is_parallel": true,
+                                    "self": 16.725447992935187,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 601.6650062590872,
+                                            "count": 678885,
+                                            "is_parallel": true,
+                                            "self": 597.1855421430863,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 4.4794641160009405,
+                                                    "count": 20,
+                                                    "is_parallel": true,
+                                                    "self": 4.4794641160009405
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 2226.516422293998,
+                                            "count": 454,
+                                            "is_parallel": true,
+                                            "self": 443.28669958297974,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 1783.2297227110182,
+                                                    "count": 23142,
+                                                    "is_parallel": true,
+                                                    "self": 1783.2297227110182
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.10783001299978423,
+                    "count": 1,
+                    "self": 0.0017079829995054752,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.10612203000027876,
+                            "count": 1,
+                            "self": 0.10612203000027876
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 599952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-599952.onnx",
+                "reward": 17.0,
+                "creation_time": 1731955366.1476102,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-599952.pt"
+                ]
+            },
+            {
+                "steps": 649896,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-649896.onnx",
+                "reward": null,
+                "creation_time": 1731955511.1726363,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-649896.pt"
+                ]
+            },
+            {
+                "steps": 699984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-699984.onnx",
+                "reward": null,
+                "creation_time": 1731955654.9433537,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-699984.pt"
+                ]
+            },
+            {
+                "steps": 749984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-749984.onnx",
+                "reward": 21.375,
+                "creation_time": 1731955798.3649225,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-749984.pt"
+                ]
+            },
+            {
+                "steps": 799880,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-799880.onnx",
+                "reward": null,
+                "creation_time": 1731955940.3511748,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-799880.pt"
+                ]
+            },
+            {
+                "steps": 849968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-849968.onnx",
+                "reward": null,
+                "creation_time": 1731956083.0957701,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-849968.pt"
+                ]
+            },
+            {
+                "steps": 899928,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-899928.onnx",
+                "reward": null,
+                "creation_time": 1731956222.6857991,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-899928.pt"
+                ]
+            },
+            {
+                "steps": 949968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-949968.onnx",
+                "reward": 21.4,
+                "creation_time": 1731956358.2106626,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-949968.pt"
+                ]
+            },
+            {
+                "steps": 999952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-999952.onnx",
+                "reward": 24.5,
+                "creation_time": 1731956498.0811203,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-999952.pt"
+                ]
+            },
+            {
+                "steps": 1000208,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000208.onnx",
+                "reward": 24.5,
+                "creation_time": 1731956498.2432156,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000208.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 1000208,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 24.5,
+            "creation_time": 1731956498.2432156,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000208.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.5.1+cu121"
+    }
+}