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: aa-unh/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 sha256:924bcd01ac61772c52659a5583350bb42933141b89a0f2c66246f5549f62e556
+size 264598

SnowballTarget/SnowballTarget-14992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a0ef6c109552a0f60eb1badf7dca51d144deb75ae1f60e3a51788260b36674f
+size 264598

SnowballTarget/SnowballTarget-14992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed072ac71190ce5161c603b7593c8f25c640b71591ca9d82e94db6504a54ab73
+size 1544400

SnowballTarget/SnowballTarget-149960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f8beb9d3fec0c20a73ca4bd1664cfbf3c377935d0a0fc03bfb9c3ce60eda17b
+size 264598

SnowballTarget/SnowballTarget-149960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99e487444b49bf68758b7900d401c87f89dd82b110e5d02071ba936f2712097d
+size 1544475

SnowballTarget/SnowballTarget-19992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7845388511a758868dcac7773c08628c15fabed62c3f06058734e1be5391dbb3
+size 264598

SnowballTarget/SnowballTarget-19992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e88c1eeea423526a136c01b573431778f967f68f375aca8ad6e6345bc78d9e5
+size 1544400

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:924bcd01ac61772c52659a5583350bb42933141b89a0f2c66246f5549f62e556
+size 264598

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2903bbfcc5542e2c497f51aefa298f79b6397573d646f736feb277edc8e42273
+size 1544475

SnowballTarget/SnowballTarget-200304.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:924bcd01ac61772c52659a5583350bb42933141b89a0f2c66246f5549f62e556
+size 264598

SnowballTarget/SnowballTarget-200304.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:672d93ef4310f7218af835a1ba683058d06808adc7127d27ee14a2102a42ff73
+size 1544475

SnowballTarget/SnowballTarget-20376.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7845388511a758868dcac7773c08628c15fabed62c3f06058734e1be5391dbb3
+size 264598

SnowballTarget/SnowballTarget-20376.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:228161b0d6234ccb79ec844874c3fbf529e52ae1157b246019b4724dd63d8e28
+size 1544400

SnowballTarget/SnowballTarget-4976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aae466529718f5c635c45fed2670cc7e65f01ff0f1834deb6bdbd5ea8a8c3c64
+size 264598

SnowballTarget/SnowballTarget-4976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:520605044822d7eb8b774230a47b21775bea87be79d6d711bb5a0a060993b735
+size 1544325

SnowballTarget/SnowballTarget-49936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d83e504de09321aa369684498cda2a23816f6e0d4f9edfe8eefa8fc189382f6
+size 264598

SnowballTarget/SnowballTarget-49936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47d7845b882e4ec488a73e46fc47f2cc56b2a88cd14349ccd6f4893456cab5c1
+size 1544400

SnowballTarget/SnowballTarget-9952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07f87f0b14fed0b3e374e58a665e02db0eaec7c21bf93110e164b0bb3ada6a86
+size 264598

SnowballTarget/SnowballTarget-9952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c4e0ef54ff7c60dd267effddb4836b19f89961575e12e4b27bbe08464eaedd0
+size 1544325

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e22491fd84bbd5afcda62ee9ccd7ee2c335935c0f642662d339c399312f803f6
+size 264598

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7054a0a4978b548dd08735e7f3212f04110693e43e731670fd2397b4340cc1ec
+size 1544400

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a067f16c6e1d243665d28b52e0177c6c9ba38bde569a21c75ce4a0029035d9a5
+size 1543650

SnowballTarget/events.out.tfevents.1710583565.34636bf01eab.3221.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:700ae8e904577e8b8ca6b99b7cb4f1740146ce9e44c933daf1efb15603cb7158
+size 35549

SnowballTarget/events.out.tfevents.1710583701.34636bf01eab.3880.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a0356ab075213fa904fd1c8cebae074aba10b867e2934f1296583375439402d
+size 17613

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": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "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": 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: 0.25
+      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: 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: 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  0.083 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: 0.676112 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]: 4837 frames, [16.0 KB-32.0 KB]: 81 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 39
+    [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]: 4919 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 6.5 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 4919 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]: 3988 frames, [64.0 KB-128.0 KB]: 931 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]: 4919 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]: 4919 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]: 4918 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]: 4919 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]: 4919 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.7 KB
+      Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -0,0 +1,377 @@
+{
+    "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 1.1718136072158813,
+            "min": 1.1718136072158813,
+            "max": 2.681352376937866,
+            "count": 18
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 11897.423828125,
+            "min": 11897.423828125,
+            "max": 27371.24609375,
+            "count": 18
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 199984.0,
+            "min": 29944.0,
+            "max": 199984.0,
+            "count": 18
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 199984.0,
+            "min": 29944.0,
+            "max": 199984.0,
+            "count": 18
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 11.82528018951416,
+            "min": 1.4653502702713013,
+            "max": 11.82528018951416,
+            "count": 18
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2305.9296875,
+            "min": 275.48583984375,
+            "max": 2390.343017578125,
+            "count": 18
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 18
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 8756.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 18
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.07201570157885012,
+            "min": 0.0623350565470972,
+            "max": 0.07762561115754685,
+            "count": 18
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.2880628063154005,
+            "min": 0.2493402261883888,
+            "max": 0.36071481362412267,
+            "count": 18
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.2164743824624548,
+            "min": 0.20455708150185792,
+            "max": 0.28092869181259006,
+            "count": 18
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.8658975298498192,
+            "min": 0.8182283260074317,
+            "max": 1.3911293531749762,
+            "count": 18
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 7.218097594000008e-06,
+            "min": 7.218097594000008e-06,
+            "max": 0.000261318012894,
+            "count": 18
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 2.8872390376000034e-05,
+            "min": 2.8872390376000034e-05,
+            "max": 0.00116634011122,
+            "count": 18
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.103609,
+            "min": 0.103609,
+            "max": 0.23065900000000003,
+            "count": 18
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.414436,
+            "min": 0.414436,
+            "max": 1.08317,
+            "count": 18
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.00013005940000000016,
+            "min": 0.00013005940000000016,
+            "max": 0.004356589400000001,
+            "count": 18
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0005202376000000006,
+            "min": 0.0005202376000000006,
+            "max": 0.019450122000000004,
+            "count": 18
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 23.75,
+            "min": 6.090909090909091,
+            "max": 23.75,
+            "count": 18
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1045.0,
+            "min": 268.0,
+            "max": 1281.0,
+            "count": 18
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 23.75,
+            "min": 6.090909090909091,
+            "max": 23.75,
+            "count": 18
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1045.0,
+            "min": 268.0,
+            "max": 1281.0,
+            "count": 18
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 18
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 18
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1710583701",
+        "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": "1710584109"
+    },
+    "total": 408.58927908399994,
+    "count": 1,
+    "self": 0.43413542099995084,
+    "children": {
+        "run_training.setup": {
+            "total": 0.05017258700002003,
+            "count": 1,
+            "self": 0.05017258700002003
+        },
+        "TrainerController.start_learning": {
+            "total": 408.10497107599997,
+            "count": 1,
+            "self": 0.553026737990649,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.881504451000069,
+                    "count": 1,
+                    "self": 1.881504451000069
+                },
+                "TrainerController.advance": {
+                    "total": 405.5932149980092,
+                    "count": 16394,
+                    "self": 0.2435399810110539,
+                    "children": {
+                        "env_step": {
+                            "total": 405.34967501699816,
+                            "count": 16394,
+                            "self": 260.27680147803096,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 144.8091394429788,
+                                    "count": 16394,
+                                    "self": 1.5757784189789845,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 143.2333610239998,
+                                            "count": 16394,
+                                            "self": 143.2333610239998
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.26373409598841135,
+                                    "count": 16394,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 407.04293591801127,
+                                            "count": 16394,
+                                            "is_parallel": true,
+                                            "self": 204.47423978801362,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0022368990000813938,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006539969999721507,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.001582902000109243,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.001582902000109243
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.03807726200000161,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0007085459998279475,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0004115870000305222,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004115870000305222
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.034970793000070444,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.034970793000070444
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.001986336000072697,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00038635200007774984,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0015999839999949472,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0015999839999949472
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 202.56869612999765,
+                                                    "count": 16393,
+                                                    "is_parallel": true,
+                                                    "self": 9.303602214014177,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 5.087042480992295,
+                                                            "count": 16393,
+                                                            "is_parallel": true,
+                                                            "self": 5.087042480992295
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 156.6499818579931,
+                                                            "count": 16393,
+                                                            "is_parallel": true,
+                                                            "self": 156.6499818579931
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 31.528069576998064,
+                                                            "count": 16393,
+                                                            "is_parallel": true,
+                                                            "self": 5.901929558991128,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 25.626140018006936,
+                                                                    "count": 163930,
+                                                                    "is_parallel": true,
+                                                                    "self": 25.626140018006936
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.0002617390000523301,
+                    "count": 1,
+                    "self": 0.0002617390000523301,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 400.19351963798294,
+                                    "count": 617215,
+                                    "is_parallel": true,
+                                    "self": 14.50065274901499,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 220.3273533709695,
+                                            "count": 617215,
+                                            "is_parallel": true,
+                                            "self": 219.83824202996936,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 0.4891113410001253,
+                                                    "count": 4,
+                                                    "is_parallel": true,
+                                                    "self": 0.4891113410001253
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 165.36551351799847,
+                                            "count": 81,
+                                            "is_parallel": true,
+                                            "self": 47.993280936991255,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 117.37223258100721,
+                                                    "count": 4128,
+                                                    "is_parallel": true,
+                                                    "self": 117.37223258100721
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.07696314999998322,
+                    "count": 1,
+                    "self": 0.000782377000177803,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.07618077299980541,
+                            "count": 1,
+                            "self": 0.07618077299980541
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 4976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-4976.onnx",
+                "reward": 2.727272727272727,
+                "creation_time": 1710583580.8054183,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-4976.pt"
+                ]
+            },
+            {
+                "steps": 9952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-9952.onnx",
+                "reward": 4.181818181818182,
+                "creation_time": 1710583592.1195774,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-9952.pt"
+                ]
+            },
+            {
+                "steps": 14992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-14992.onnx",
+                "reward": 5.0,
+                "creation_time": 1710583602.9728162,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-14992.pt"
+                ]
+            },
+            {
+                "steps": 19992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-19992.onnx",
+                "reward": 5.0,
+                "creation_time": 1710583614.8861253,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-19992.pt"
+                ]
+            },
+            {
+                "steps": 20376,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-20376.onnx",
+                "reward": 5.0,
+                "creation_time": 1710583615.0230784,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-20376.pt"
+                ]
+            },
+            {
+                "steps": 49936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 9.727272727272727,
+                "creation_time": 1710583772.4091961,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                ]
+            },
+            {
+                "steps": 99960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 15.818181818181818,
+                "creation_time": 1710583883.9867408,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                ]
+            },
+            {
+                "steps": 149960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149960.onnx",
+                "reward": 21.636363636363637,
+                "creation_time": 1710583995.9376435,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149960.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 23.09090909090909,
+                "creation_time": 1710584109.0403361,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 200304,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200304.onnx",
+                "reward": 23.09090909090909,
+                "creation_time": 1710584109.1613553,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200304.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 200304,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 23.09090909090909,
+            "creation_time": 1710584109.1613553,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200304.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.2.1+cu121"
+    }
+}