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: bobobert4/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:e442260048cb1fd0580820e8e71b6cd24da625735e831be978b58d9b0be3e9f0
+size 260484

SnowballTarget/SnowballTarget-119952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0de3fd161a40da2b4173b301be1c0d798200c930f4d96d10c06a1fe9cac83ca
+size 260484

SnowballTarget/SnowballTarget-119952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f303487061faafef70ef24851d78ead04f07b75e3831cfe58fd115448561fd6
+size 784804

SnowballTarget/SnowballTarget-129992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d64c9a32406c0cb128f944855d856fedb3fcdc11c7c7b6cc189f8443261b994c
+size 260484

SnowballTarget/SnowballTarget-129992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b50a0139758ef569fa2bdad75c250033db02c949bd779429617904d5266b2c46
+size 784804

SnowballTarget/SnowballTarget-139944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29de04c0de41e70e2724db8bb7f78d57572235f9d16cab13b8fc480b5d3af899
+size 260484

SnowballTarget/SnowballTarget-139944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6414222c259c03e2a9c342c0e2b37ade74a812956c804a4a572e73ea860d226
+size 784804

SnowballTarget/SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaef15a4e34dbd9de398add022ad218a1a2788cd7bbe6746336be19e3c5247a7
+size 260484

SnowballTarget/SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cea3eddbc856fbc1c96bfe62b6a91134a5f7be711088ab961cc0c172da36d839
+size 784804

SnowballTarget/SnowballTarget-159936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73df06950f8744f2e36921a51f938de352943caca8fec8732033f31ba15ad100
+size 260484

SnowballTarget/SnowballTarget-159936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b016409537d964666c1a21db95cbae18ffce30ae31fec2a4985f07860fede3d0
+size 784804

SnowballTarget/SnowballTarget-169976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29c0dc0436f6f73fb7409cc7377c0445e634b6cfa25bcde027927f0db7d0c62e
+size 260484

SnowballTarget/SnowballTarget-169976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c9caecbbe72fe0e67ab2170ca423f11b8d7699ef2acd7cb9ee090b8cadcde65
+size 784804

SnowballTarget/SnowballTarget-179928.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88be180da6f6ca32369baf1375e5b5d68150aa6562cd8bf54154cb379373159a
+size 260484

SnowballTarget/SnowballTarget-179928.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b51939ba31199884f03604d1663ed164422f707b54fabb576f338b8270c0131e
+size 784804

SnowballTarget/SnowballTarget-189968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8864f572f2eac09ecab7d3ac001cbdbe3ab2d5519290a67db2cf2eb1749d28cd
+size 260484

SnowballTarget/SnowballTarget-189968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:287fb928ba9d5c26431e3d12e2877b1642fd6670a06996648dca0f73e8904982
+size 784804

SnowballTarget/SnowballTarget-199920.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e442260048cb1fd0580820e8e71b6cd24da625735e831be978b58d9b0be3e9f0
+size 260484

SnowballTarget/SnowballTarget-199920.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a957895df5abd8b84b3ef28cb0b2444bbbc356a4b11a6a061607c397c1f777b
+size 784804

SnowballTarget/SnowballTarget-200112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e442260048cb1fd0580820e8e71b6cd24da625735e831be978b58d9b0be3e9f0
+size 260484

SnowballTarget/SnowballTarget-200112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe8ac531dd03c6c9329ff7a6835994a182545cd977e846220e4a347e319ddac0
+size 784804

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe8ac531dd03c6c9329ff7a6835994a182545cd977e846220e4a347e319ddac0
+size 784804

SnowballTarget/events.out.tfevents.1689914871.4ba227ddcbc5.2356.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a56f9f3435198e1fa05879dbef68d285e06b2677c7dcd079400665ede499629c
+size 45584

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": 0.25, "lambd": 0.95, "num_epoch": 5, "shared_critic": true, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 10000, "network_settings": {"normalize": false, "hidden_units": 128, "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": 200000, "time_horizon": 96, "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, "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: 0.25
+      lambd: 0.95
+      num_epoch: 5
+      shared_critic: true
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 10000
+    network_settings:
+      normalize: false
+      hidden_units: 128
+      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: 200000
+    time_horizon: 96
+    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
+  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: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  0.082 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: 0.673895 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]: 5374 frames, [16.0 KB-32.0 KB]: 91 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]: 5466 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 6.7 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 5466 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]: 4365 frames, [64.0 KB-128.0 KB]: 1101 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]: 5466 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]: 5466 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]: 5465 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]: 5466 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]: 5466 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": 0.9074764847755432,
+            "min": 0.8980207443237305,
+            "max": 2.887725353240967,
+            "count": 40
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 4102.701171875,
+            "min": 4102.701171875,
+            "max": 16009.548828125,
+            "count": 40
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 199920.0,
+            "min": 4976.0,
+            "max": 199920.0,
+            "count": 40
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 199920.0,
+            "min": 4976.0,
+            "max": 199920.0,
+            "count": 40
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 12.52747631072998,
+            "min": 0.09490196406841278,
+            "max": 12.592220306396484,
+            "count": 40
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 901.978271484375,
+            "min": 6.83294153213501,
+            "max": 1038.786865234375,
+            "count": 40
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 40
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 6567.0,
+            "min": 4378.0,
+            "max": 6567.0,
+            "count": 40
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.07068405189210727,
+            "min": 0.06319188880186309,
+            "max": 0.07711656137079818,
+            "count": 40
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.14136810378421455,
+            "min": 0.12638377760372618,
+            "max": 0.22135205152216098,
+            "count": 40
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.20135490622590568,
+            "min": 0.10407538581091691,
+            "max": 0.2827119831653202,
+            "count": 40
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.40270981245181137,
+            "min": 0.20815077162183382,
+            "max": 0.7716041477287517,
+            "count": 40
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 4.782098406000002e-06,
+            "min": 4.782098406000002e-06,
+            "max": 0.000295182001606,
+            "count": 40
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 9.564196812000005e-06,
+            "min": 9.564196812000005e-06,
+            "max": 0.0008211960262679999,
+            "count": 40
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10239100000000001,
+            "min": 0.10239100000000001,
+            "max": 0.24759100000000003,
+            "count": 40
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.20478200000000002,
+            "min": 0.20478200000000002,
+            "max": 0.7105980000000001,
+            "count": 40
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 8.954060000000004e-05,
+            "min": 8.954060000000004e-05,
+            "max": 0.004919860599999999,
+            "count": 40
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.00017908120000000008,
+            "min": 0.00017908120000000008,
+            "max": 0.0136892268,
+            "count": 40
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 24.772727272727273,
+            "min": 2.8636363636363638,
+            "max": 25.09090909090909,
+            "count": 40
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 545.0,
+            "min": 63.0,
+            "max": 808.0,
+            "count": 40
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 24.772727272727273,
+            "min": 2.8636363636363638,
+            "max": 25.09090909090909,
+            "count": 40
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 545.0,
+            "min": 63.0,
+            "max": 808.0,
+            "count": 40
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 40
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 40
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1689914868",
+        "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./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": "1689915421"
+    },
+    "total": 552.590371831,
+    "count": 1,
+    "self": 0.8758308999999826,
+    "children": {
+        "run_training.setup": {
+            "total": 0.03300840200006405,
+            "count": 1,
+            "self": 0.03300840200006405
+        },
+        "TrainerController.start_learning": {
+            "total": 551.6815325289999,
+            "count": 1,
+            "self": 0.6336164739990409,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 6.078368554999997,
+                    "count": 1,
+                    "self": 6.078368554999997
+                },
+                "TrainerController.advance": {
+                    "total": 544.7398578980009,
+                    "count": 18218,
+                    "self": 0.30483696400312965,
+                    "children": {
+                        "env_step": {
+                            "total": 544.4350209339977,
+                            "count": 18218,
+                            "self": 397.6144213920046,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 146.50968025798602,
+                                    "count": 18218,
+                                    "self": 1.9840145679867192,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 144.5256656899993,
+                                            "count": 18218,
+                                            "self": 144.5256656899993
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.3109192840071273,
+                                    "count": 18218,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 549.7212558960065,
+                                            "count": 18218,
+                                            "is_parallel": true,
+                                            "self": 284.3714180130047,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0063523060000534315,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.004795859000068958,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0015564469999844732,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0015564469999844732
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.0849465590000591,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0009313829999655354,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0004525500000909233,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004525500000909233
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.08036101599998347,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.08036101599998347
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0032016100000191727,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0007062609996637548,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.002495349000355418,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.002495349000355418
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 265.3498378830018,
+                                                    "count": 18217,
+                                                    "is_parallel": true,
+                                                    "self": 11.18796804900171,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 5.470085376996963,
+                                                            "count": 18217,
+                                                            "is_parallel": true,
+                                                            "self": 5.470085376996963
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 212.13326891400357,
+                                                            "count": 18217,
+                                                            "is_parallel": true,
+                                                            "self": 212.13326891400357
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 36.558515542999544,
+                                                            "count": 18217,
+                                                            "is_parallel": true,
+                                                            "self": 7.096372885992309,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 29.462142657007234,
+                                                                    "count": 182170,
+                                                                    "is_parallel": true,
+                                                                    "self": 29.462142657007234
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.00027281200004836137,
+                    "count": 1,
+                    "self": 0.00027281200004836137,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 541.8961593720343,
+                                    "count": 354203,
+                                    "is_parallel": true,
+                                    "self": 7.870481475088809,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 215.14901628794598,
+                                            "count": 354203,
+                                            "is_parallel": true,
+                                            "self": 210.52944220694633,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 4.619574080999655,
+                                                    "count": 20,
+                                                    "is_parallel": true,
+                                                    "self": 4.619574080999655
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 318.8766616089995,
+                                            "count": 90,
+                                            "is_parallel": true,
+                                            "self": 125.46813759000077,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 193.40852401899872,
+                                                    "count": 7645,
+                                                    "is_parallel": true,
+                                                    "self": 193.40852401899872
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.2294167899999593,
+                    "count": 1,
+                    "self": 0.0010001840000768425,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.22841660599988245,
+                            "count": 1,
+                            "self": 0.22841660599988245
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 119952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-119952.onnx",
+                "reward": 21.454545454545453,
+                "creation_time": 1689915197.0312555,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-119952.pt"
+                ]
+            },
+            {
+                "steps": 129992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-129992.onnx",
+                "reward": 22.636363636363637,
+                "creation_time": 1689915226.046242,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-129992.pt"
+                ]
+            },
+            {
+                "steps": 139944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-139944.onnx",
+                "reward": 24.90909090909091,
+                "creation_time": 1689915251.506197,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-139944.pt"
+                ]
+            },
+            {
+                "steps": 149984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 23.818181818181817,
+                "creation_time": 1689915279.6826274,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                ]
+            },
+            {
+                "steps": 159936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-159936.onnx",
+                "reward": 24.0,
+                "creation_time": 1689915305.8110385,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-159936.pt"
+                ]
+            },
+            {
+                "steps": 169976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-169976.onnx",
+                "reward": 24.181818181818183,
+                "creation_time": 1689915334.796858,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-169976.pt"
+                ]
+            },
+            {
+                "steps": 179928,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-179928.onnx",
+                "reward": 25.454545454545453,
+                "creation_time": 1689915363.8239555,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-179928.pt"
+                ]
+            },
+            {
+                "steps": 189968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-189968.onnx",
+                "reward": 24.0,
+                "creation_time": 1689915393.1039462,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-189968.pt"
+                ]
+            },
+            {
+                "steps": 199920,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199920.onnx",
+                "reward": 23.90909090909091,
+                "creation_time": 1689915420.3405128,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199920.pt"
+                ]
+            },
+            {
+                "steps": 200112,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 23.90909090909091,
+                "creation_time": 1689915420.6127658,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 200112,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 23.90909090909091,
+            "creation_time": 1689915420.6127658,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}