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: Gleb1441/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 sha256:18486d404f95c9e8f270472f3c8de72a3e99038b6463b7009444325155aa3840
+size 650646

SnowballTarget/SnowballTarget-0.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23334f5cdfa480a8485774ed8ee07aaaf8cfefa942049c91e28e7c4daea67008
+size 649740

SnowballTarget/SnowballTarget-0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89bb8e03182d2faecac8ca3f44ca05ae34642a9233c0d86692d8da5648506607
+size 1285975

SnowballTarget/SnowballTarget-2200.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f961b8ba727e815c70f986b859838519db7fb9074952192b756e70fe5d609d3
+size 649740

SnowballTarget/SnowballTarget-2200.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c27fb0d6ca1391b0efe0236b16dd780abd9969e5d7ec6870722554510a2bfeb4
+size 1286056

SnowballTarget/SnowballTarget-299800.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:664531c580089a396595320e7a3b9f23e3e367ec261ee93bab0c4b51681fbcf7
+size 650646

SnowballTarget/SnowballTarget-299800.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e533606cf77490f83ec2c67c58d4ab15f6f03a818db780f39d72d38e848a59ed
+size 3849710

SnowballTarget/SnowballTarget-349800.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f6e04d5b917eedce1d33072ae3c80a7de0be233734e53e832736a0a78d1bf07
+size 650646

SnowballTarget/SnowballTarget-349800.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1a3ffd0ab1a83a479f1465771efb5f1959588f8838d1622ff9e980a5172a617
+size 3849710

SnowballTarget/SnowballTarget-399800.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36911ff5df0523821d4e6401bab44f7b301d7b773968bceeff8a868d65ef90f2
+size 650646

SnowballTarget/SnowballTarget-399800.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94707ac5250d28288a120d76404025ab9e6c06f328ef6d0ebb79d33b0f7055bd
+size 3849710

SnowballTarget/SnowballTarget-449800.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c1ba62215dd7fb23815581fe68756f535e75ab1904364785f0e23a7860dcdeb
+size 650646

SnowballTarget/SnowballTarget-449800.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40a7f067fefaa4eed701e14aaf1f20b8e2ee782d3918faf67b83c3346d342316
+size 3849710

SnowballTarget/SnowballTarget-499800.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8643ce138172f8c0847f7959f5e553af5348099d47e86cbfdaef6172b30b06a
+size 650646

SnowballTarget/SnowballTarget-499800.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a87ca6bce6e59c1a8a982f3d94b60110f29d6809370efbc70acf0908fcb4ae12
+size 3849710

SnowballTarget/SnowballTarget-549800.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac9f82c57339fdd0ad7321dc28a2502945cd214d2d3f73028b5824ea64b944dc
+size 650646

SnowballTarget/SnowballTarget-549800.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9d322e20280fdaba6ba12bb7ed5c0aa38f3b5e87962f5451aa904b5c1fdaaec
+size 3849710

SnowballTarget/SnowballTarget-599800.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ff833ca0bee1aad16ab8da7dcc4d1335f7dce828a13d7edbae67f44542e1cfb
+size 650646

SnowballTarget/SnowballTarget-599800.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebbc91a0b5130455fdfbec6b91496970d584c2ee17720124c2cc42c58625d330
+size 3849710

SnowballTarget/SnowballTarget-649800.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dce2414c6530659d5ab44be02aa7330a284f415b9e986a7a7e21d3197ebca8f1
+size 650646

SnowballTarget/SnowballTarget-649800.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0c68ac16e0f839e324d9a5f836de79b30580f12132e3a2c831b80e4ed136450
+size 3849710

SnowballTarget/SnowballTarget-699800.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18486d404f95c9e8f270472f3c8de72a3e99038b6463b7009444325155aa3840
+size 650646

SnowballTarget/SnowballTarget-699800.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e959b5c5dcf0fd2188275099cd04b9fd8a446c2c56713ca4fdaa5e0113853b9
+size 3849710

SnowballTarget/SnowballTarget-701800.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18486d404f95c9e8f270472f3c8de72a3e99038b6463b7009444325155aa3840
+size 650646

SnowballTarget/SnowballTarget-701800.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f70ae8656164509a9f5f67a6afc2d9ca525308b2240f57970f72fc52f50c57ea
+size 3849710

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d61682578bd4781a637360b71cd1a4d13d073a07db54a94048f414a4a13e991
+size 3848821

SnowballTarget/events.out.tfevents.1781589940.d11aa5d54211.17582.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d527f78adacee6615ff6ef878abd126d41877e9d7ca6e65356a2c5f53f96f68
+size 64528

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 256, "buffer_size": 2048, "learning_rate": 0.001, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 700000, "time_horizon": 256, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": 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: 2048
+      learning_rate: 0.001
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 50000
+    network_settings:
+      normalize: false
+      hidden_units: 256
+      num_layers: 2
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+    init_path: null
+    keep_checkpoints: 10
+    even_checkpoints: false
+    max_steps: 700000
+    time_horizon: 256
+    summary_freq: 10000
+    threaded: true
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  timeout_wait: 60
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: SnowballTarget1
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: true
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,259 @@
+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'
+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  0.083 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: 0.783864 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]: 18823 frames, [16.0 KB-32.0 KB]: 319 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.0 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 198 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 304.0 KB
+      Peak Allocated Bytes 228.9 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 40
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 11780 frames, [8.0 MB-16.0 MB]: 7363 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 10.9 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 19143 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]: 18684 frames, [64.0 KB-128.0 KB]: 459 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]: 19143 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]: 19143 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]: 19142 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]: 19143 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]: 19143 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": 0.5145233869552612,
+            "min": 0.5145233869552612,
+            "max": 2.8660833835601807,
+            "count": 70
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 5631.45849609375,
+            "min": 4595.94921875,
+            "max": 31747.60546875,
+            "count": 70
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 70
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 10945.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 70
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 699800.0,
+            "min": 9800.0,
+            "max": 699800.0,
+            "count": 70
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 699800.0,
+            "min": 9800.0,
+            "max": 699800.0,
+            "count": 70
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 14.108232498168945,
+            "min": 0.3773690462112427,
+            "max": 14.246672630310059,
+            "count": 70
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 705.41162109375,
+            "min": 18.4910831451416,
+            "max": 712.3336181640625,
+            "count": 70
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 27.68,
+            "min": 2.7755102040816326,
+            "max": 28.4,
+            "count": 70
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1384.0,
+            "min": 136.0,
+            "max": 1420.0,
+            "count": 70
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 27.68,
+            "min": 2.7755102040816326,
+            "max": 28.4,
+            "count": 70
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1384.0,
+            "min": 136.0,
+            "max": 1420.0,
+            "count": 70
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.043044207071943674,
+            "min": 0.034920364098430426,
+            "max": 0.05579220969617989,
+            "count": 70
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.21522103535971837,
+            "min": 0.1396814563937217,
+            "max": 0.2789610484808994,
+            "count": 70
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.17004195228219032,
+            "min": 0.11393281910568476,
+            "max": 0.31102832704782485,
+            "count": 70
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.8502097614109516,
+            "min": 0.45573127642273903,
+            "max": 1.5551416352391243,
+            "count": 70
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 6.857242171428565e-06,
+            "min": 6.857242171428565e-06,
+            "max": 0.0009921428579285714,
+            "count": 70
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 3.4286210857142825e-05,
+            "min": 3.4286210857142825e-05,
+            "max": 0.004890000011000001,
+            "count": 70
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.1006857142857143,
+            "min": 0.1006857142857143,
+            "max": 0.19921428571428576,
+            "count": 70
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.5034285714285714,
+            "min": 0.40840000000000004,
+            "max": 0.989,
+            "count": 70
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 4.421714285714282e-05,
+            "min": 4.421714285714282e-05,
+            "max": 0.004960792857142858,
+            "count": 70
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.00022108571428571411,
+            "min": 0.00022108571428571411,
+            "max": 0.0244511,
+            "count": 70
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 70
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 70
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1781589939",
+        "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
+        "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": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.8.0+cu128",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1781591777"
+    },
+    "total": 1837.4215608340005,
+    "count": 1,
+    "self": 0.47631639199971687,
+    "children": {
+        "run_training.setup": {
+            "total": 0.02647557400041478,
+            "count": 1,
+            "self": 0.02647557400041478
+        },
+        "TrainerController.start_learning": {
+            "total": 1836.9187688680004,
+            "count": 1,
+            "self": 2.3825179219866186,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.6619302489998518,
+                    "count": 1,
+                    "self": 2.6619302489998518
+                },
+                "TrainerController.advance": {
+                    "total": 1831.7934550390146,
+                    "count": 63807,
+                    "self": 1.0248483731356828,
+                    "children": {
+                        "env_step": {
+                            "total": 1830.768606665879,
+                            "count": 63807,
+                            "self": 1131.8993143629723,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 697.8171795669773,
+                                    "count": 63807,
+                                    "self": 5.611469959815167,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 692.2057096071621,
+                                            "count": 63807,
+                                            "self": 692.2057096071621
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 1.0521127359293132,
+                                    "count": 63807,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 1830.7343053119612,
+                                            "count": 63807,
+                                            "is_parallel": true,
+                                            "self": 867.667243464914,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.002205762999892613,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006677570004285371,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.001538005999464076,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.001538005999464076
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.08324944500009224,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006333189999168098,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00044682499992632074,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00044682499992632074
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.07878374400024768,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.07878374400024768
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.003385557000001427,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004515180012276687,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.002934038998773758,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.002934038998773758
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 963.0670618470472,
+                                                    "count": 63806,
+                                                    "is_parallel": true,
+                                                    "self": 41.00977993215247,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 21.309366140884322,
+                                                            "count": 63806,
+                                                            "is_parallel": true,
+                                                            "self": 21.309366140884322
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 745.3081576158988,
+                                                            "count": 63806,
+                                                            "is_parallel": true,
+                                                            "self": 745.3081576158988
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 155.43975815811154,
+                                                            "count": 63806,
+                                                            "is_parallel": true,
+                                                            "self": 29.699138919318557,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 125.74061923879299,
+                                                                    "count": 638060,
+                                                                    "is_parallel": true,
+                                                                    "self": 125.74061923879299
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.0012713669993900112,
+                    "count": 1,
+                    "self": 0.0012713669993900112,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 1810.8553188466021,
+                                    "count": 2360083,
+                                    "is_parallel": true,
+                                    "self": 56.025633100267896,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 1128.9643205633292,
+                                            "count": 2360083,
+                                            "is_parallel": true,
+                                            "self": 1126.9115021663297,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 2.0528183969995553,
+                                                    "count": 14,
+                                                    "is_parallel": true,
+                                                    "self": 2.0528183969995553
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 625.865365183005,
+                                            "count": 318,
+                                            "is_parallel": true,
+                                            "self": 183.00152960402602,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 442.863835578979,
+                                                    "count": 7632,
+                                                    "is_parallel": true,
+                                                    "self": 442.863835578979
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.07959429099992121,
+                    "count": 1,
+                    "self": 0.0010057780000352068,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.078588512999886,
+                            "count": 1,
+                            "self": 0.078588512999886
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 299800,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299800.onnx",
+                "reward": 26.333333333333332,
+                "creation_time": 1781590770.5407915,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-299800.pt"
+                ]
+            },
+            {
+                "steps": 349800,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349800.onnx",
+                "reward": null,
+                "creation_time": 1781590897.7612667,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-349800.pt"
+                ]
+            },
+            {
+                "steps": 399800,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399800.onnx",
+                "reward": 25.625,
+                "creation_time": 1781591019.7103388,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-399800.pt"
+                ]
+            },
+            {
+                "steps": 449800,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449800.onnx",
+                "reward": 28.2,
+                "creation_time": 1781591146.0617795,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-449800.pt"
+                ]
+            },
+            {
+                "steps": 499800,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499800.onnx",
+                "reward": 28.0,
+                "creation_time": 1781591274.3709998,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-499800.pt"
+                ]
+            },
+            {
+                "steps": 549800,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-549800.onnx",
+                "reward": 28.8,
+                "creation_time": 1781591397.9173226,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-549800.pt"
+                ]
+            },
+            {
+                "steps": 599800,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-599800.onnx",
+                "reward": 27.857142857142858,
+                "creation_time": 1781591524.9277875,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-599800.pt"
+                ]
+            },
+            {
+                "steps": 649800,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-649800.onnx",
+                "reward": 26.75,
+                "creation_time": 1781591651.2748277,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-649800.pt"
+                ]
+            },
+            {
+                "steps": 699800,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-699800.onnx",
+                "reward": 28.0,
+                "creation_time": 1781591776.3330767,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-699800.pt"
+                ]
+            },
+            {
+                "steps": 701800,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-701800.onnx",
+                "reward": 28.09090909090909,
+                "creation_time": 1781591776.6082814,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-701800.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 701800,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 28.09090909090909,
+            "creation_time": 1781591776.6082814,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-701800.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.8.0+cu128"
+    }
+}