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: Klimxo/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 sha256:6e0f4453537e689372743a265e04ed66921406e00b6c434ce3ab78fabd048c8a
+size 2874755

SnowballTarget/SnowballTarget-124968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:142ea9069c5085bb8bd619b632381aa261be0a9beedd1384339122bedd7b3037
+size 2874755

SnowballTarget/SnowballTarget-124968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd4253c3d06e7468d28940006c9f55ae9b0324eca7d30656a01bb71f34752d63
+size 17149478

SnowballTarget/SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a4302436950468510a5bc15749ab1ba443cd83a9d47337a12bc8f67baffd9bd
+size 2874755

SnowballTarget/SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fb67d8fe7b34b0ccf46c325521e8468eb1b6b93b12a8ed81343bbe1e6779a85
+size 17149478

SnowballTarget/SnowballTarget-174952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0975f2d05b629f3d221eb47a2f0b40af08d2ec14c187e19cb7de33cb92f86cc9
+size 2874755

SnowballTarget/SnowballTarget-174952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6ac114e1405b2dda5ce9f4aed3afc16344b0105419b764ff71dfe7ed7755c05
+size 17149478

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:075cb20fae778cf3735a693b2c1a4d880a54165fc2d5c104517b21bc2df12b49
+size 2874755

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:044d4185be2341904fdac8d1b9ab4cb840f953a337392b228ba16d7c250edec1
+size 17149478

SnowballTarget/SnowballTarget-224912.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:461af0c7f500967958ffa3000a5a038a824ec2669cbd556fbd2d0426c12a3862
+size 2874755

SnowballTarget/SnowballTarget-224912.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b0cfaacdedb3dad47f6524199b05d29fb70e78b5db4c7481d4cb0f83d2210f3
+size 17149478

SnowballTarget/SnowballTarget-249880.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e2bfad083e78d8d9dd6b057e02abd623557ca75e8caa0297ab5aa043cbefb65
+size 2874755

SnowballTarget/SnowballTarget-249880.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a680c808910e47f52693fd22ce635a4a7406929690b31c77c645c96924645d4
+size 17149478

SnowballTarget/SnowballTarget-250800.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e0f4453537e689372743a265e04ed66921406e00b6c434ce3ab78fabd048c8a
+size 2874755

SnowballTarget/SnowballTarget-250800.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87004857982ce5fa1587ef45938bbea6f253557b35bd0d53d5e13aea280dd558
+size 17149478

SnowballTarget/SnowballTarget-49952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3349ba17469f008ba2c08c90a9beab11a14278a3179b169b48b279df2074ca0c
+size 2874755

SnowballTarget/SnowballTarget-49952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:862c4dadf736e8341da0a3df51fbf4fa5450fbd19390415cbc08f857e49fc71d
+size 17149357

SnowballTarget/SnowballTarget-74928.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9da0f6f75cf4786a84267b1337188c99a51a12a123a03195e04d53ce870301a8
+size 2874755

SnowballTarget/SnowballTarget-74928.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:928ee9a4198a29f96b02fcd2c459d86c3ab375e82a79ff2a95c885766454fa50
+size 17149357

SnowballTarget/SnowballTarget-99896.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2ba293c98c3cee98d7e2c16e708750a741eeea805a019f97d21677c3f5d9c8b
+size 2874755

SnowballTarget/SnowballTarget-99896.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a411455eacec3cb81063014fd1dba7401f8706656646d904471be461d150f37a
+size 17149357

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abc31a02b6c053914a9d78933fed65bff7bf28cd2b917ce0385241da2253ac98
+size 17148147

SnowballTarget/events.out.tfevents.1727023442.83fd9f431d19.1982.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdb33f2f74f42d26776b321d65366bcb6addac9ef80acebd5412eb7611a535ca
+size 63249

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 256, "buffer_size": 4096, "learning_rate": 0.0002, "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": 25000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 500000, "time_horizon": 128, "summary_freq": 5000, "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: 256
+      buffer_size: 4096
+      learning_rate: 0.0002
+      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: 25000
+    network_settings:
+      normalize: true
+      hidden_units: 512
+      num_layers: 3
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.995
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+    init_path: null
+    keep_checkpoints: 10
+    even_checkpoints: false
+    max_steps: 500000
+    time_horizon: 128
+    summary_freq: 5000
+    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  0.088 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: 0.669764 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]: 6769 frames, [16.0 KB-32.0 KB]: 114 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 45
+    [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]: 6884 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 7.1 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 6884 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]: 6477 frames, [64.0 KB-128.0 KB]: 407 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 66.8 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 6884 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]: 6884 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]: 6883 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]: 6884 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]: 6884 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": 1.283064603805542,
+            "min": 1.283064603805542,
+            "max": 2.8894717693328857,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 5716.052734375,
+            "min": 5716.052734375,
+            "max": 19197.650390625,
+            "count": 50
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 249880.0,
+            "min": 4912.0,
+            "max": 249880.0,
+            "count": 50
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 249880.0,
+            "min": 4912.0,
+            "max": 249880.0,
+            "count": 50
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 24.551767349243164,
+            "min": 0.02715410105884075,
+            "max": 24.551767349243164,
+            "count": 50
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 1178.48486328125,
+            "min": 1.3033968210220337,
+            "max": 1228.746826171875,
+            "count": 50
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 50
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 4378.0,
+            "min": 4378.0,
+            "max": 6567.0,
+            "count": 50
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 26.272727272727273,
+            "min": 2.6818181818181817,
+            "max": 26.51851851851852,
+            "count": 50
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 578.0,
+            "min": 59.0,
+            "max": 779.0,
+            "count": 50
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 26.272727272727273,
+            "min": 2.6818181818181817,
+            "max": 26.51851851851852,
+            "count": 50
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 578.0,
+            "min": 59.0,
+            "max": 779.0,
+            "count": 50
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.050374415147063485,
+            "min": 0.03606104990193511,
+            "max": 0.05759636968209901,
+            "count": 50
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.050374415147063485,
+            "min": 0.03606104990193511,
+            "max": 0.10187350098614628,
+            "count": 50
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.1911360056961284,
+            "min": 0.09473218321800232,
+            "max": 0.3654931355925167,
+            "count": 50
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.1911360056961284,
+            "min": 0.09473218321800232,
+            "max": 0.6713911156443988,
+            "count": 50
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 0.00010144004927999997,
+            "min": 0.00010144004927999997,
+            "max": 0.00019824000088,
+            "count": 50
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 0.00010144004927999997,
+            "min": 0.00010144004927999997,
+            "max": 0.00037008001496,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.15071999999999997,
+            "min": 0.15071999999999997,
+            "max": 0.19912,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.15071999999999997,
+            "min": 0.15071999999999997,
+            "max": 0.38504000000000005,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.002540928,
+            "min": 0.002540928,
+            "max": 0.004956088000000001,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.002540928,
+            "min": 0.002540928,
+            "max": 0.009253496000000002,
+            "count": 50
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 50
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 50
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1727023442",
+        "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 --force",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.4.1+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1727024172"
+    },
+    "total": 729.994286358,
+    "count": 1,
+    "self": 0.010999842999922294,
+    "children": {
+        "run_training.setup": {
+            "total": 0.05049896100001661,
+            "count": 1,
+            "self": 0.05049896100001661
+        },
+        "TrainerController.start_learning": {
+            "total": 729.932787554,
+            "count": 1,
+            "self": 1.7766083020130736,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.0671965389999514,
+                    "count": 1,
+                    "self": 2.0671965389999514
+                },
+                "TrainerController.advance": {
+                    "total": 725.889319640987,
+                    "count": 22945,
+                    "self": 0.39339196298783463,
+                    "children": {
+                        "env_step": {
+                            "total": 725.4959276779991,
+                            "count": 22945,
+                            "self": 570.5068757080278,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 154.62392303297833,
+                                    "count": 22945,
+                                    "self": 1.9456735979693462,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 152.67824943500898,
+                                            "count": 22945,
+                                            "self": 152.67824943500898
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.36512893699301685,
+                                    "count": 22944,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 727.3554420830012,
+                                            "count": 22944,
+                                            "is_parallel": true,
+                                            "self": 451.258439566992,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.002133714000024156,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006227190000913652,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.001510994999932791,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.001510994999932791
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.03648735100000522,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006408929999679458,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00040243900002678856,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00040243900002678856
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.032155583000019305,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.032155583000019305
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0032884359999911794,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00042584900006659154,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.002862586999924588,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.002862586999924588
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 276.0970025160092,
+                                                    "count": 22943,
+                                                    "is_parallel": true,
+                                                    "self": 12.622228944000028,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 6.639933890009161,
+                                                            "count": 22943,
+                                                            "is_parallel": true,
+                                                            "self": 6.639933890009161
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 216.36968423000405,
+                                                            "count": 22943,
+                                                            "is_parallel": true,
+                                                            "self": 216.36968423000405
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 40.46515545199594,
+                                                            "count": 22943,
+                                                            "is_parallel": true,
+                                                            "self": 7.693580631968018,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 32.77157482002792,
+                                                                    "count": 229430,
+                                                                    "is_parallel": true,
+                                                                    "self": 32.77157482002792
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 6.491400017694104e-05,
+                    "count": 1,
+                    "self": 6.491400017694104e-05,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 718.2388507330124,
+                                    "count": 537962,
+                                    "is_parallel": true,
+                                    "self": 10.010347316031357,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 246.09446945398065,
+                                            "count": 537963,
+                                            "is_parallel": true,
+                                            "self": 243.2749854109809,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 2.819484042999761,
+                                                    "count": 10,
+                                                    "is_parallel": true,
+                                                    "self": 2.819484042999761
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 462.1340339630005,
+                                            "count": 56,
+                                            "is_parallel": true,
+                                            "self": 96.58517024600252,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 365.54886371699797,
+                                                    "count": 4785,
+                                                    "is_parallel": true,
+                                                    "self": 365.54886371699797
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.19959815799984426,
+                    "count": 1,
+                    "self": 0.004359148999810714,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.19523900900003355,
+                            "count": 1,
+                            "self": 0.19523900900003355
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 49952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49952.onnx",
+                "reward": 13.5,
+                "creation_time": 1727023585.2521598,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49952.pt"
+                ]
+            },
+            {
+                "steps": 74928,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-74928.onnx",
+                "reward": null,
+                "creation_time": 1727023660.0377128,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-74928.pt"
+                ]
+            },
+            {
+                "steps": 99896,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99896.onnx",
+                "reward": 19.181818181818183,
+                "creation_time": 1727023724.9556286,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99896.pt"
+                ]
+            },
+            {
+                "steps": 124968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-124968.onnx",
+                "reward": 20.6,
+                "creation_time": 1727023796.75207,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-124968.pt"
+                ]
+            },
+            {
+                "steps": 149984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": null,
+                "creation_time": 1727023873.0166008,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                ]
+            },
+            {
+                "steps": 174952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-174952.onnx",
+                "reward": 22.818181818181817,
+                "creation_time": 1727023941.261797,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-174952.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 24.0,
+                "creation_time": 1727024017.3907359,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 224912,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-224912.onnx",
+                "reward": null,
+                "creation_time": 1727024096.413262,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-224912.pt"
+                ]
+            },
+            {
+                "steps": 249880,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249880.onnx",
+                "reward": 25.545454545454547,
+                "creation_time": 1727024165.7711194,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-249880.pt"
+                ]
+            },
+            {
+                "steps": 250800,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-250800.onnx",
+                "reward": null,
+                "creation_time": 1727024172.120689,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-250800.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 250800,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": null,
+            "creation_time": 1727024172.120689,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-250800.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.4.1+cu121"
+    }
+}