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: beibeif/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 sha256:22af25d594016e1f0ffb597c5b8a0b882345894c633c104b0642aaeb1792fe2d
+size 650646

SnowballTarget/SnowballTarget-19992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2412cdfc771ece66b6b71cb0ab989908c945d6912530358f7970e938a9ae4d74
+size 650646

SnowballTarget/SnowballTarget-19992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d293bfb891974a93f33e57df8f7971583790b7f7070a162716ba328c398fad19
+size 3850000

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfdc8b72ffc867a48653176c981eb77843cdc8aa6b6b36aa4ecd77f2c906bc5
+size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3b75cccbef0c11a8a7aa3cb6329de5c24f7f397d06cf93a5fcbccda7c5b3074
+size 3850075

SnowballTarget/SnowballTarget-299968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a56e418306ec58d3f44106881efc91c71f6de63ed479953b1377cd8bf627a56
+size 650646

SnowballTarget/SnowballTarget-299968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b02bdc128d64f9185267bf97acda2f9ec2e6ed283a6fd58ea48fd2a3e9c9df32
+size 3850075

SnowballTarget/SnowballTarget-39984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cfa2aaf6b63fcc402f5ea65b7c2b03f1318d8fea735f572b24a7be0f1480403
+size 650646

SnowballTarget/SnowballTarget-39984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:618be06d55ab7747fc3cacfc9cb33bb66031a4e0bbd7f9f6792441d1cf7d8593
+size 3850000

SnowballTarget/SnowballTarget-399992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22af25d594016e1f0ffb597c5b8a0b882345894c633c104b0642aaeb1792fe2d
+size 650646

SnowballTarget/SnowballTarget-399992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75bf7a2c99f552d8db09b5c10ca53dfcafb3bae5da9c35df542e9f4b4c3ba36f
+size 3850075

SnowballTarget/SnowballTarget-400312.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22af25d594016e1f0ffb597c5b8a0b882345894c633c104b0642aaeb1792fe2d
+size 650646

SnowballTarget/SnowballTarget-400312.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a1a472d08b46b81664239075a89abea0d756546fdde03b6b22d2af20b17d0dc
+size 3850075

SnowballTarget/SnowballTarget-59976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc14a05b041291393546c1ec360ccb7801e700d4a210ad8feece9f7ce5b51075
+size 650646

SnowballTarget/SnowballTarget-59976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d4e7d0966672d4955ebda81110fc5471ad4df853f156c46ff0d69b62d6ae289
+size 3850000

SnowballTarget/SnowballTarget-79968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9842b70c4e9da69b9abfea7a249ea783fcc2a427d6db6bcf2e9ea22ad7fcf01e
+size 650646

SnowballTarget/SnowballTarget-79968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b905255ed8702c2b1241bf13d13333dc4e99f468daed33c2e97419fc0fa3a025
+size 3850000

SnowballTarget/SnowballTarget-93104.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e62dc2108152e0304bd8fc0e50b6992809bc0c3f103a63891b0fcd3a75a7a304
+size 650646

SnowballTarget/SnowballTarget-93104.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef5d979ac81a6c5c9c151f8810c701d337bb4e20faf14bf23d6f1efaca62439e
+size 3850000

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e88f4234afee5f6c44ba62c0031b067f0a311c7ee0a0c11d37b45c9eff02d082
+size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c78e03400772be00a7ddc2086be2e8d7fc4116e75b6d6ae91f3295aa5a7a857f
+size 3850000

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fe867dc3a26f96a45ddb3111c03816e65b4eb34184edcab1132007da726b7e4
+size 3849250

SnowballTarget/events.out.tfevents.1705547664.d6a020a38654.4783.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70f7091da15bae8e3c22187e6c999a389ec74c02457280fd8321c6a486c0b087
+size 18969

SnowballTarget/events.out.tfevents.1705548027.d6a020a38654.6390.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ae39c8d3dc8ddd17fea3ab8b4f87cad76e011236d22792450ee83cb185f1ed5
+size 31694

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": 100000, "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": 400000, "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: 100000
+    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: 400000
+    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  0.135 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: 1.007408 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]: 8241 frames, [16.0 KB-32.0 KB]: 139 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 36
+    [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]: 8381 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 7.5 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 8381 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]: 8144 frames, [64.0 KB-128.0 KB]: 237 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 66.0 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 8381 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]: 8381 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]: 8380 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]: 8381 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]: 8381 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": 0.7069892883300781,
+            "min": 0.701500654220581,
+            "max": 1.35214102268219,
+            "count": 31
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 7263.60791015625,
+            "min": 6682.4951171875,
+            "max": 12372.3984375,
+            "count": 31
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 399992.0,
+            "min": 99960.0,
+            "max": 399992.0,
+            "count": 31
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 399992.0,
+            "min": 99960.0,
+            "max": 399992.0,
+            "count": 31
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 13.631186485290527,
+            "min": 10.57642936706543,
+            "max": 13.664360046386719,
+            "count": 31
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2794.393310546875,
+            "min": 1438.3944091796875,
+            "max": 2794.393310546875,
+            "count": 31
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 31
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 10945.0,
+            "min": 6567.0,
+            "max": 10945.0,
+            "count": 31
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06780927591459533,
+            "min": 0.061376927880933095,
+            "max": 0.07793927635208878,
+            "count": 31
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.3390463795729767,
+            "min": 0.20087032251438927,
+            "max": 0.3725462593153466,
+            "count": 31
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.17066708014291873,
+            "min": 0.1640759305115424,
+            "max": 0.23118937921290306,
+            "count": 31
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.8533354007145937,
+            "min": 0.6563037220461696,
+            "max": 1.1111377445506114,
+            "count": 31
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 4.1880986039999985e-06,
+            "min": 4.1880986039999985e-06,
+            "max": 0.00022693802435399995,
+            "count": 31
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 2.0940493019999994e-05,
+            "min": 2.0940493019999994e-05,
+            "max": 0.00106869014377,
+            "count": 31
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.101396,
+            "min": 0.101396,
+            "max": 0.175646,
+            "count": 31
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.50698,
+            "min": 0.415484,
+            "max": 0.85623,
+            "count": 31
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 7.966039999999998e-05,
+            "min": 7.966039999999998e-05,
+            "max": 0.0037847353999999997,
+            "count": 31
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0003983019999999999,
+            "min": 0.0003983019999999999,
+            "max": 0.017825877000000004,
+            "count": 31
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 27.054545454545455,
+            "min": 23.454545454545453,
+            "max": 27.295454545454547,
+            "count": 31
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1488.0,
+            "min": 774.0,
+            "max": 1488.0,
+            "count": 31
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 27.054545454545455,
+            "min": 23.454545454545453,
+            "max": 27.295454545454547,
+            "count": 31
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1488.0,
+            "min": 774.0,
+            "max": 1488.0,
+            "count": 31
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 31
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 31
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1705548026",
+        "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 --resume --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.1.2+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1705548777"
+    },
+    "total": 751.715977307,
+    "count": 1,
+    "self": 0.4263679019998108,
+    "children": {
+        "run_training.setup": {
+            "total": 0.08411890800016408,
+            "count": 1,
+            "self": 0.08411890800016408
+        },
+        "TrainerController.start_learning": {
+            "total": 751.205490497,
+            "count": 1,
+            "self": 1.018838512995444,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.0977821469998617,
+                    "count": 1,
+                    "self": 2.0977821469998617
+                },
+                "TrainerController.advance": {
+                    "total": 747.9950774040046,
+                    "count": 27934,
+                    "self": 0.4866754869817669,
+                    "children": {
+                        "env_step": {
+                            "total": 747.5084019170229,
+                            "count": 27934,
+                            "self": 496.0701771360307,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 250.94414513200195,
+                                    "count": 27934,
+                                    "self": 2.5930723539818246,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 248.35107277802013,
+                                            "count": 27934,
+                                            "self": 248.35107277802013
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.4940796489902368,
+                                    "count": 27934,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 749.0841753540183,
+                                            "count": 27934,
+                                            "is_parallel": true,
+                                            "self": 365.9215478160097,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.001956782999968709,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.000598297000351522,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0013584859996171872,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0013584859996171872
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.03954676700004711,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006104980002419325,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00041545399994902255,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00041545399994902255
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.03649741399999584,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.03649741399999584
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.002023400999860314,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00040651200038155366,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0016168889994787605,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0016168889994787605
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 383.16262753800856,
+                                                    "count": 27933,
+                                                    "is_parallel": true,
+                                                    "self": 17.462785774014264,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 9.064425476015458,
+                                                            "count": 27933,
+                                                            "is_parallel": true,
+                                                            "self": 9.064425476015458
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 298.38481820302286,
+                                                            "count": 27933,
+                                                            "is_parallel": true,
+                                                            "self": 298.38481820302286
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 58.25059808495598,
+                                                            "count": 27933,
+                                                            "is_parallel": true,
+                                                            "self": 11.008855524902856,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 47.241742560053126,
+                                                                    "count": 279330,
+                                                                    "is_parallel": true,
+                                                                    "self": 47.241742560053126
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.00029002900009800214,
+                    "count": 1,
+                    "self": 0.00029002900009800214,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 738.1164579088861,
+                                    "count": 1118723,
+                                    "is_parallel": true,
+                                    "self": 25.38489415857248,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 406.93031082931293,
+                                            "count": 1118723,
+                                            "is_parallel": true,
+                                            "self": 406.39530816431306,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 0.5350026649998654,
+                                                    "count": 4,
+                                                    "is_parallel": true,
+                                                    "self": 0.5350026649998654
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 305.8012529210007,
+                                            "count": 139,
+                                            "is_parallel": true,
+                                            "self": 99.3436938169989,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 206.4575591040018,
+                                                    "count": 7080,
+                                                    "is_parallel": true,
+                                                    "self": 206.4575591040018
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.09350240399999166,
+                    "count": 1,
+                    "self": 0.0012314699997659773,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.09227093400022568,
+                            "count": 1,
+                            "self": 0.09227093400022568
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 19992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-19992.onnx",
+                "reward": 7.818181818181818,
+                "creation_time": 1705547717.9299064,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-19992.pt"
+                ]
+            },
+            {
+                "steps": 39984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-39984.onnx",
+                "reward": 11.818181818181818,
+                "creation_time": 1705547765.3070986,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-39984.pt"
+                ]
+            },
+            {
+                "steps": 59976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-59976.onnx",
+                "reward": 17.636363636363637,
+                "creation_time": 1705547815.373155,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-59976.pt"
+                ]
+            },
+            {
+                "steps": 79968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-79968.onnx",
+                "reward": 19.818181818181817,
+                "creation_time": 1705547864.428472,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-79968.pt"
+                ]
+            },
+            {
+                "steps": 93104,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-93104.onnx",
+                "reward": 21.454545454545453,
+                "creation_time": 1705547896.406652,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-93104.pt"
+                ]
+            },
+            {
+                "steps": 99960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 24.09090909090909,
+                "creation_time": 1705548047.0973115,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 27.545454545454547,
+                "creation_time": 1705548288.845745,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 299968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.onnx",
+                "reward": 27.09090909090909,
+                "creation_time": 1705548533.2564316,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.pt"
+                ]
+            },
+            {
+                "steps": 399992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.onnx",
+                "reward": 27.545454545454547,
+                "creation_time": 1705548777.3040059,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.pt"
+                ]
+            },
+            {
+                "steps": 400312,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-400312.onnx",
+                "reward": 27.545454545454547,
+                "creation_time": 1705548777.4459052,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-400312.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 400312,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 27.545454545454547,
+            "creation_time": 1705548777.4459052,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-400312.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.1.2+cu121"
+    }
+}