First Push

README.md

@@ -0,0 +1,29 @@
+---
+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://github.com/huggingface/ml-agents#get-started
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+
+
+  ### Resume the training
+  ```
+  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. Go to https://huggingface.co/spaces/unity/ML-Agents-SnowballTarget
+  2. Step 1: Find your model_id: dvesely/ppo-SnowballTargetTESTCOLAB
+  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 sha256:362bb3f0a5b895c6f3e9f9f98408c565db6a7360ccc84b9d8dd0c385b6677675
+size 2862900

SnowballTarget/SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23b293cacdeae059ce2d79e7b26612cfc9a5bb14be77cfe6c5f3c7d63364a2f4
+size 2862900

SnowballTarget/SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bfe973a2be370b0fab0367350e5343109bea3f1d5185d8f020204eb22faba00
+size 17122012

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89f35886a3826f0698daa7bd9ff45d710c45bdd64d027b8338dd042becbf17c3
+size 2862900

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfd56c4f99b4062a47f7bf6f5a3ff3ce0c188ad51af7f1b10a6f8bccfe4bb453
+size 17122012

SnowballTarget/SnowballTarget-249944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:557cd257426d6946e37277fb6d8596ae4e0250f07d1cfd509bd91770c9ced3e8
+size 2862900

SnowballTarget/SnowballTarget-249944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:413f333e7d9ae30d5e4f5b1defabc2ec8a70bf0984179d89fa1606e170b429dc
+size 17122012

SnowballTarget/SnowballTarget-299968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:642025c5016e72d3b591555eeb86a3d8532f157eed2fd318add74518ac0d00e0
+size 2862900

SnowballTarget/SnowballTarget-299968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22a005daee9756926be6b5396e69a4f4f5aeffadd33d9772062a752fcbbb9171
+size 17122012

SnowballTarget/SnowballTarget-349992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21339bef5ccf9d65ed7393874cc4f5875eb7fad70141068dd32f7e48fef6e924
+size 2862900

SnowballTarget/SnowballTarget-349992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e3654bb0fd309d3bd4c6dfa7ce9857f34ed1bd0357123b1b1da913953a5402a
+size 17122012

SnowballTarget/SnowballTarget-399992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a4e33bc2477d2a06ddca96de3c59e2f68b1c1effa73e1966192ba20d2ed1b40
+size 2862900

SnowballTarget/SnowballTarget-399992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e233bb54c383952064829f3c6f09ba2cd48e604868d0a9fe0f7198008213a9
+size 17122012

SnowballTarget/SnowballTarget-449952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74dcb4aa19486ba02f4ea1f5ff4f821278bdf70817a3104e933748d611598a11
+size 2862900

SnowballTarget/SnowballTarget-449952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:490c60f85c4c421c61bbdcaef8b6a97eeabcf4d9867aec1c1a7c874d5805c8cc
+size 17122012

SnowballTarget/SnowballTarget-499976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:362bb3f0a5b895c6f3e9f9f98408c565db6a7360ccc84b9d8dd0c385b6677675
+size 2862900

SnowballTarget/SnowballTarget-499976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d69437bf546e70f7847acdf98ab088ce3c91e178d8072bf269a4273a7021400
+size 17122012

SnowballTarget/SnowballTarget-500104.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:362bb3f0a5b895c6f3e9f9f98408c565db6a7360ccc84b9d8dd0c385b6677675
+size 2862900

SnowballTarget/SnowballTarget-500104.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d888bc9d901bf74717d7389cd59d1df834fcdf8ae0eb33186fd226de1bc6d2bc
+size 17122012

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9c79da331fc08c0c7a946b2aeb60b94fcb4df08859ffc16990b158829c13096
+size 2862900

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fef798f9073e76e6bbac2ce06c56f8a8d8b92c9e78efe0738396204b4838928
+size 17122012

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d888bc9d901bf74717d7389cd59d1df834fcdf8ae0eb33186fd226de1bc6d2bc
+size 17122012

SnowballTarget/events.out.tfevents.1682765831.7e93209d637b.3867.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a47e8b04c217344bad2541ca51f6622053d8849da7906d3d3df9085ad21a070
+size 43280

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 4, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 500000, "time_horizon": 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, "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}, "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 +1,77 @@
+default_settings: null
+behaviors:
+  SnowballTarget:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 2048
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 4
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 50000
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 3
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+    init_path: null
+    keep_checkpoints: 10
+    even_checkpoints: false
+    max_steps: 500000
+    time_horizon: 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
+  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
+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:767:(parse_card) cannot find card '0'
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
+ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5220:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2642:(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:767:(parse_card) cannot find card '0'
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
+ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5220:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2642:(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  0.080 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: 0.634997 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]: 13423 frames, [16.0 KB-32.0 KB]: 227 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.0 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 198 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 304.0 KB
+      Peak Allocated Bytes 228.9 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 41
+    [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]: 10457 frames, [8.0 MB-16.0 MB]: 3194 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 10.1 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 13651 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.3 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]: 13111 frames, [64.0 KB-128.0 KB]: 540 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 66.7 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 13651 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]: 13651 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]: 13650 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]: 13651 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]: 13651 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": 0.7193920016288757,
+            "min": 0.644972026348114,
+            "max": 2.8559772968292236,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 6979.541015625,
+            "min": 6230.97412109375,
+            "max": 29279.48046875,
+            "count": 50
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 499976.0,
+            "min": 9952.0,
+            "max": 499976.0,
+            "count": 50
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 499976.0,
+            "min": 9952.0,
+            "max": 499976.0,
+            "count": 50
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 13.947929382324219,
+            "min": 0.4451306462287903,
+            "max": 14.07044792175293,
+            "count": 50
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2859.325439453125,
+            "min": 86.3553466796875,
+            "max": 2870.371337890625,
+            "count": 50
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 50
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 10945.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 50
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06430221184643468,
+            "min": 0.06278411294539075,
+            "max": 0.07612753370374455,
+            "count": 50
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.32151105923217344,
+            "min": 0.251136451781563,
+            "max": 0.3735430156133696,
+            "count": 50
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.15254325649755843,
+            "min": 0.14308350027045783,
+            "max": 0.2767700690447408,
+            "count": 50
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.7627162824877921,
+            "min": 0.5796235216891064,
+            "max": 1.373644238228307,
+            "count": 50
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 3.0528989824000028e-06,
+            "min": 3.0528989824000028e-06,
+            "max": 0.00029675280108239997,
+            "count": 50
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 1.5264494912000015e-05,
+            "min": 1.5264494912000015e-05,
+            "max": 0.0014540640153119996,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10101760000000001,
+            "min": 0.10101760000000001,
+            "max": 0.1989176,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.5050880000000001,
+            "min": 0.41199040000000003,
+            "max": 0.984688,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 6.0778240000000044e-05,
+            "min": 6.0778240000000044e-05,
+            "max": 0.00494598824,
+            "count": 50
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0003038912000000002,
+            "min": 0.0003038912000000002,
+            "max": 0.0242359312,
+            "count": 50
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 27.30909090909091,
+            "min": 4.318181818181818,
+            "max": 27.477272727272727,
+            "count": 50
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1502.0,
+            "min": 190.0,
+            "max": 1510.0,
+            "count": 50
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 27.30909090909091,
+            "min": 4.318181818181818,
+            "max": 27.477272727272727,
+            "count": 50
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1502.0,
+            "min": 190.0,
+            "max": 1510.0,
+            "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": "1682765831",
+        "python_version": "3.9.16 (main, Dec  7 2022, 01:11:51) \n[GCC 9.4.0]",
+        "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": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.11.0+cu102",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1682767043"
+    },
+    "total": 1211.921904452,
+    "count": 1,
+    "self": 0.7475630860001274,
+    "children": {
+        "run_training.setup": {
+            "total": 0.059591299999965486,
+            "count": 1,
+            "self": 0.059591299999965486
+        },
+        "TrainerController.start_learning": {
+            "total": 1211.114750066,
+            "count": 1,
+            "self": 1.2875781180132435,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 4.4236449590000575,
+                    "count": 1,
+                    "self": 4.4236449590000575
+                },
+                "TrainerController.advance": {
+                    "total": 1205.0875946819867,
+                    "count": 45501,
+                    "self": 0.7013152209931377,
+                    "children": {
+                        "env_step": {
+                            "total": 1204.3862794609936,
+                            "count": 45501,
+                            "self": 907.5355454139674,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 296.209017691006,
+                                    "count": 45501,
+                                    "self": 4.211431683007163,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 291.99758600799885,
+                                            "count": 45501,
+                                            "self": 291.99758600799885
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.641716356020197,
+                                    "count": 45501,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 1207.4213552510369,
+                                            "count": 45501,
+                                            "is_parallel": true,
+                                            "self": 605.096152877025,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.005515705999982856,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.004112745999805156,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0014029600001776998,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0014029600001776998
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.07085110100001657,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.006187852999914867,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00040852100005395187,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00040852100005395187
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.06241750799995316,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.06241750799995316
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.001837219000094592,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003749050000578791,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.001462314000036713,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.001462314000036713
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 602.3252023740118,
+                                                    "count": 45500,
+                                                    "is_parallel": true,
+                                                    "self": 23.957158885989543,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 12.959156301995108,
+                                                            "count": 45500,
+                                                            "is_parallel": true,
+                                                            "self": 12.959156301995108
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 488.60255535303634,
+                                                            "count": 45500,
+                                                            "is_parallel": true,
+                                                            "self": 488.60255535303634
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 76.80633183299085,
+                                                            "count": 45500,
+                                                            "is_parallel": true,
+                                                            "self": 14.946446573914727,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 61.85988525907612,
+                                                                    "count": 455000,
+                                                                    "is_parallel": true,
+                                                                    "self": 61.85988525907612
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.0001044529999489896,
+                    "count": 1,
+                    "self": 0.0001044529999489896,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 1196.2852658851039,
+                                    "count": 1041870,
+                                    "is_parallel": true,
+                                    "self": 24.8510988141943,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 608.8936082789104,
+                                            "count": 1041870,
+                                            "is_parallel": true,
+                                            "self": 604.5513481869104,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 4.342260091999947,
+                                                    "count": 10,
+                                                    "is_parallel": true,
+                                                    "self": 4.342260091999947
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 562.540558791999,
+                                            "count": 227,
+                                            "is_parallel": true,
+                                            "self": 222.3576635050016,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 340.18289528699745,
+                                                    "count": 15432,
+                                                    "is_parallel": true,
+                                                    "self": 340.18289528699745
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.3158278539999628,
+                    "count": 1,
+                    "self": 0.0034862089999023738,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.31234164500006045,
+                            "count": 1,
+                            "self": 0.31234164500006045
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 99960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 23.90909090909091,
+                "creation_time": 1682766077.3915079,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                ]
+            },
+            {
+                "steps": 149984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 25.181818181818183,
+                "creation_time": 1682766198.4134722,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 26.272727272727273,
+                "creation_time": 1682766317.5079432,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 249944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.onnx",
+                "reward": 26.90909090909091,
+                "creation_time": 1682766437.8943508,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.pt"
+                ]
+            },
+            {
+                "steps": 299968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.onnx",
+                "reward": 26.363636363636363,
+                "creation_time": 1682766559.5268073,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.pt"
+                ]
+            },
+            {
+                "steps": 349992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.onnx",
+                "reward": 26.90909090909091,
+                "creation_time": 1682766678.7215765,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.pt"
+                ]
+            },
+            {
+                "steps": 399992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.onnx",
+                "reward": 26.181818181818183,
+                "creation_time": 1682766798.2626243,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.pt"
+                ]
+            },
+            {
+                "steps": 449952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.onnx",
+                "reward": 27.727272727272727,
+                "creation_time": 1682766919.8864982,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.pt"
+                ]
+            },
+            {
+                "steps": 499976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499976.onnx",
+                "reward": 27.272727272727273,
+                "creation_time": 1682767042.024333,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-499976.pt"
+                ]
+            },
+            {
+                "steps": 500104,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.onnx",
+                "reward": 27.272727272727273,
+                "creation_time": 1682767042.3742394,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 500104,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 27.272727272727273,
+            "creation_time": 1682767042.3742394,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}