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: Croolch/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 sha256:4b40ae90aa2a647489bb621f5a71a31155e415be440a973683b63eaa6ebf028e
+size 650646

SnowballTarget/SnowballTarget-106304.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fa05cb253ab7df0b9017e282c4a34aff0b52e6b32494a9c3b4ff547566d87ef
+size 650646

SnowballTarget/SnowballTarget-106304.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee76ae46d371ae9e46af65dc34fed63c71082e93540a31ba7f6f238e56e4002b
+size 3850075

SnowballTarget/SnowballTarget-149960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc00fb26e7e2419e26848b94c7a75c27998833cba088cf03e03317a9e2d6bc6b
+size 650646

SnowballTarget/SnowballTarget-149960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c235ae7a34048c9a1637c318427941929a86ecba26f0456ca884f497d3fb6d4d
+size 3850075

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f23912c681c4a22e0386656917e9674ac82953973f83511e1316bd4d91bfc838
+size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd7ab5fdf775bd1b4a2463f4ffbe6501edd695b166b95cf0c92570d2508b0b7e
+size 3850075

SnowballTarget/SnowballTarget-249944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c881b4e1ba2ec7c04904473cc1bb90b7b95c776c72502d72a64fc71e2a03e3c
+size 650646

SnowballTarget/SnowballTarget-249944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4c5c0728cafd01f3508b3534f7ed9b3705ca5450fc1ce94e5edabcb6b739878
+size 3850075

SnowballTarget/SnowballTarget-299968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b80a7b22b84a1b32a17b8a1074ebe69ee8f493fd48cad60b8041580e55db9018
+size 650646

SnowballTarget/SnowballTarget-299968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82a1a550420ddc50015720f84139bcd948ae3292830c5cb10b9c536da45f91fa
+size 3850075

SnowballTarget/SnowballTarget-349968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b087aca49498e6b6c45b5e085f44bdf61423608e90ca5b876c02a20ffa61966
+size 650646

SnowballTarget/SnowballTarget-349968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29903384d4fc76c6b21da07837d62615b2e1da6dd22b50ea8763c276c6500357
+size 3850075

SnowballTarget/SnowballTarget-399992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc44e77e302b3570da69566ebf41f94eadbd35d7124b7bc49e3bacec5c54ff2d
+size 650646

SnowballTarget/SnowballTarget-399992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e3236008559417ac50d9bc947c8e3de44a0308ecb038c7fa165116e7037b9bb
+size 3850075

SnowballTarget/SnowballTarget-449952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:770b01ba87067594303f2a82f9598b1332fc205acf8dc0f8fb2d61a481a4cf31
+size 650646

SnowballTarget/SnowballTarget-449952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0926d470a0ae3a5adc9d1db00649c325fa70849c4f36e1cded4d143915ec97b
+size 3850075

SnowballTarget/SnowballTarget-499952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2537220b604274e215281ff63360d7e8d416fe5bcee419aa92ae0e4186dc05d4
+size 650646

SnowballTarget/SnowballTarget-499952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc5c724953e5e9954f817295e259a76d5c7f65166229db2d9eb86333aba7391d
+size 3850075

SnowballTarget/SnowballTarget-503712.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b40ae90aa2a647489bb621f5a71a31155e415be440a973683b63eaa6ebf028e
+size 650646

SnowballTarget/SnowballTarget-503712.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec49884764a01094e089de1bf81f0c2bb2239304717bc1adb0e8285d27b01aa8
+size 3850075

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1021930e6c37713772ca8622a5efa3aaa222395874e3ea25d764e7f1fc6e8ab
+size 3849250

SnowballTarget/events.out.tfevents.1710409200.37b084e5a0d8.2639.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c386752a18392989e49270506fd5a903accc908b5885ccd76f8b8a8ac238950
+size 15565

SnowballTarget/events.out.tfevents.1710409479.37b084e5a0d8.3907.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e153b99c35542636f315e066aa04f629462637efbfa320f2360930e853bf4e5a
+size 34075

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": 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": 2000000, "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, "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": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,79 @@
+default_settings: null
+behaviors:
+  SnowballTarget:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 2048
+      learning_rate: 0.0003
+      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: 2000000
+    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
+  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: true
+  force: false
+  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  0.082 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: 0.735953 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]: 10663 frames, [16.0 KB-32.0 KB]: 180 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]: 10840 frames, [8.0 MB-16.0 MB]: 4 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 8.8 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 10844 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]: 9998 frames, [64.0 KB-128.0 KB]: 846 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]: 10844 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]: 10844 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]: 10843 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]: 10844 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]: 10844 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": 0.864636242389679,
+            "min": 0.8203649520874023,
+            "max": 1.5189265012741089,
+            "count": 40
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 8255.546875,
+            "min": 6549.611328125,
+            "max": 13609.1630859375,
+            "count": 40
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 499952.0,
+            "min": 109976.0,
+            "max": 499952.0,
+            "count": 40
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 499952.0,
+            "min": 109976.0,
+            "max": 499952.0,
+            "count": 40
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 13.8157377243042,
+            "min": 9.369784355163574,
+            "max": 13.842137336730957,
+            "count": 40
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2694.06884765625,
+            "min": 627.7755737304688,
+            "max": 2813.323974609375,
+            "count": 40
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 40
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 8756.0,
+            "min": 2189.0,
+            "max": 10945.0,
+            "count": 40
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06334171503291217,
+            "min": 0.04622214240589528,
+            "max": 0.08125960973739697,
+            "count": 40
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.25336686013164866,
+            "min": 0.04622214240589528,
+            "max": 0.4062980486869849,
+            "count": 40
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.16826069588754694,
+            "min": 0.1534993161757787,
+            "max": 0.23228520873714897,
+            "count": 40
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.6730427835501878,
+            "min": 0.21794966142624617,
+            "max": 1.1614260436857449,
+            "count": 40
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 0.0002258226247258,
+            "min": 0.0002258226247258,
+            "max": 0.00028373760542079997,
+            "count": 40
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 0.0009032904989032,
+            "min": 0.00028373760542079997,
+            "max": 0.001413738028754,
+            "count": 40
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.17527420000000005,
+            "min": 0.17527420000000005,
+            "max": 0.19457919999999998,
+            "count": 40
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.7010968000000002,
+            "min": 0.19457919999999998,
+            "max": 0.9712459999999998,
+            "count": 40
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.00376618258,
+            "min": 0.00376618258,
+            "max": 0.00472950208,
+            "count": 40
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.01506473032,
+            "min": 0.00472950208,
+            "max": 0.023565175400000006,
+            "count": 40
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 26.954545454545453,
+            "min": 19.545454545454547,
+            "max": 27.295454545454547,
+            "count": 40
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1186.0,
+            "min": 215.0,
+            "max": 1495.0,
+            "count": 40
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 26.954545454545453,
+            "min": 19.545454545454547,
+            "max": 27.295454545454547,
+            "count": 40
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1186.0,
+            "min": 215.0,
+            "max": 1495.0,
+            "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": "1710409478",
+        "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.2.1+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1710410323"
+    },
+    "total": 844.5671383540001,
+    "count": 1,
+    "self": 0.7400595080001722,
+    "children": {
+        "run_training.setup": {
+            "total": 0.05052030699994248,
+            "count": 1,
+            "self": 0.05052030699994248
+        },
+        "TrainerController.start_learning": {
+            "total": 843.776558539,
+            "count": 1,
+            "self": 1.0151436209880558,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.9490691789999346,
+                    "count": 1,
+                    "self": 1.9490691789999346
+                },
+                "TrainerController.advance": {
+                    "total": 840.653146659012,
+                    "count": 36144,
+                    "self": 0.47874007598784374,
+                    "children": {
+                        "env_step": {
+                            "total": 840.1744065830242,
+                            "count": 36144,
+                            "self": 541.7318599540237,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 297.92083471402145,
+                                    "count": 36144,
+                                    "self": 2.779346825999255,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 295.1414878880222,
+                                            "count": 36144,
+                                            "self": 295.1414878880222
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.5217119149790506,
+                                    "count": 36143,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 841.5461368460287,
+                                            "count": 36143,
+                                            "is_parallel": true,
+                                            "self": 420.92967734005924,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0022644880000370904,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006113540001706497,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0016531339998664407,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0016531339998664407
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.03597519000004468,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006587450001234174,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0003920949999383083,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003920949999383083
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.032972031999975115,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.032972031999975115
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0019523180000078355,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.000377611000089928,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0015747069999179075,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0015747069999179075
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 420.6164595059695,
+                                                    "count": 36142,
+                                                    "is_parallel": true,
+                                                    "self": 19.541282589966954,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 10.276662951010394,
+                                                            "count": 36142,
+                                                            "is_parallel": true,
+                                                            "self": 10.276662951010394
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 326.67533893098596,
+                                                            "count": 36142,
+                                                            "is_parallel": true,
+                                                            "self": 326.67533893098596
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 64.12317503400618,
+                                                            "count": 36142,
+                                                            "is_parallel": true,
+                                                            "self": 11.733031465923773,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 52.39014356808241,
+                                                                    "count": 361420,
+                                                                    "is_parallel": true,
+                                                                    "self": 52.39014356808241
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 4.357400007393153e-05,
+                    "count": 1,
+                    "self": 4.357400007393153e-05,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 830.2605510590836,
+                                    "count": 1237395,
+                                    "is_parallel": true,
+                                    "self": 26.987675326179442,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 457.0546465729017,
+                                            "count": 1237395,
+                                            "is_parallel": true,
+                                            "self": 455.615314869902,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 1.4393317029996524,
+                                                    "count": 8,
+                                                    "is_parallel": true,
+                                                    "self": 1.4393317029996524
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 346.21822916000247,
+                                            "count": 180,
+                                            "is_parallel": true,
+                                            "self": 98.40025826000647,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 247.817970899996,
+                                                    "count": 9177,
+                                                    "is_parallel": true,
+                                                    "self": 247.817970899996
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.15915550599993367,
+                    "count": 1,
+                    "self": 0.0023052929998357286,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.15685021300009794,
+                            "count": 1,
+                            "self": 0.15685021300009794
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 106304,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-106304.onnx",
+                "reward": 19.818181818181817,
+                "creation_time": 1710409429.7283494,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-106304.pt"
+                ]
+            },
+            {
+                "steps": 149960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149960.onnx",
+                "reward": 22.818181818181817,
+                "creation_time": 1710409575.644283,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149960.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 25.727272727272727,
+                "creation_time": 1710409681.9822364,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 249944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.onnx",
+                "reward": 26.181818181818183,
+                "creation_time": 1710409788.4153483,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.pt"
+                ]
+            },
+            {
+                "steps": 299968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.onnx",
+                "reward": 27.272727272727273,
+                "creation_time": 1710409894.7375097,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.pt"
+                ]
+            },
+            {
+                "steps": 349968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349968.onnx",
+                "reward": 26.727272727272727,
+                "creation_time": 1710409998.4044063,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-349968.pt"
+                ]
+            },
+            {
+                "steps": 399992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.onnx",
+                "reward": 26.545454545454547,
+                "creation_time": 1710410104.9861393,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.pt"
+                ]
+            },
+            {
+                "steps": 449952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.onnx",
+                "reward": 28.09090909090909,
+                "creation_time": 1710410209.3427505,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.pt"
+                ]
+            },
+            {
+                "steps": 499952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499952.onnx",
+                "reward": 28.09090909090909,
+                "creation_time": 1710410314.6505299,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-499952.pt"
+                ]
+            },
+            {
+                "steps": 503712,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-503712.onnx",
+                "reward": 26.727272727272727,
+                "creation_time": 1710410322.5602026,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-503712.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 503712,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 26.727272727272727,
+            "creation_time": 1710410322.5602026,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-503712.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.2.1+cu121"
+    }
+}