First Push

README.md

@@ -0,0 +1,29 @@
+---
+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://github.com/huggingface/ml-agents#get-started
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+
+
+  ### Resume the training
+  ```
+  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. Go to https://huggingface.co/spaces/unity/ML-Agents-SnowballTarget
+  2. Step 1: Find your model_id: xavisgg/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 sha256:22e04b80a4056a249341ee814d7c7d5fe5d39f44d4835ca6f18e24721c0df4c5
+size 646532

SnowballTarget/SnowballTarget-119952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:989f1690260003f76e65467cf6c8a18976fe28376e347f364ba431248a55c9a7
+size 646532

SnowballTarget/SnowballTarget-119952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6583ae62bae7a987d9e58f41c2ce7885b4dc311bfa68e24bb82bb598c5d869cd
+size 3843968

SnowballTarget/SnowballTarget-139944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb701f792dd089b21c6b24322ba2a8d7f1ab7b91aee22fe6bb105448264e910d
+size 646532

SnowballTarget/SnowballTarget-139944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a674572f5fc8542989a982331a17d6db4abb0333dc0b3f4e29a328945eef896
+size 3843968

SnowballTarget/SnowballTarget-159936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87ecf8266846c8a5362810effa103fa8d358972e63db1b312e0a6494b1d784b4
+size 646532

SnowballTarget/SnowballTarget-159936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dd6e10f3f3cc1566b0fe138f71235459c7efadf24c466a4fcff8e0eca6696c7
+size 3843968

SnowballTarget/SnowballTarget-179992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e2add6374153d54550d96989c89ccf0f6175b633eb7d67d57e68ec13f16a158
+size 646532

SnowballTarget/SnowballTarget-179992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8500586c7e37eb94603f0087af7e64bb71ec786b24db6c633a69641994447253
+size 3843968

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d4c6b2c6e778706deaf7080008e956ef985d297023c0dae0ab50f8af8213bb6
+size 646532

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ebaf654c00a1b275c5ec886bd5e71d268d5ec3af81e00afe3bfe3b590c35f77
+size 3843968

SnowballTarget/SnowballTarget-219992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22e04b80a4056a249341ee814d7c7d5fe5d39f44d4835ca6f18e24721c0df4c5
+size 646532

SnowballTarget/SnowballTarget-219992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aadb57c8b664ec919a79ad8d4597ef98861a93a7b8da4843849464c8ba3bece
+size 3843968

SnowballTarget/SnowballTarget-220576.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22e04b80a4056a249341ee814d7c7d5fe5d39f44d4835ca6f18e24721c0df4c5
+size 646532

SnowballTarget/SnowballTarget-220576.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb68388c0e87c18f81573ac907d4ee6845b4c5c960b13cb87ff10c16443a1e75
+size 3843968

SnowballTarget/SnowballTarget-59976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d7b218e0fa0eb2f739b83bd8d2ec32c8338655e92190ec9eab8dbc485c1479b
+size 646532

SnowballTarget/SnowballTarget-59976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6a5b24a0d62747ae2fa92692530bbc03256ad81862e52e8da3d1330a819a156
+size 3843968

SnowballTarget/SnowballTarget-79968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:874d53c61d55ffad46caedb08de119b5485f2ed3079125dec5c74eba96fbe1ad
+size 646532

SnowballTarget/SnowballTarget-79968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3c1571a5f0ba44b307e7db80ce09277907e3cff3c31d56e4a98410043ddb179
+size 3843968

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a52149489e6b4214c3c595ddc0b39dce7302b88a1a94eb9d4af0afc8635af03c
+size 646532

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd63e3f504a7762475f5ab7c90e1f81644f6b0cf2102e7dcb151920fb9e3edc3
+size 3843968

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb68388c0e87c18f81573ac907d4ee6845b4c5c960b13cb87ff10c16443a1e75
+size 3843968

SnowballTarget/events.out.tfevents.1680251071.cf258a28d646.7429.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12678d47758512441d2eba23843534394f78f44c141b44b78e87ffe8ff5031ec
+size 25344

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": 20000, "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": 220000, "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, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,77 @@
+default_settings: null
+behaviors:
+  SnowballTarget:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 2048
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 20000
+    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: 220000
+    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
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+environment_parameters: null
+checkpoint_settings:
+  run_id: SnowballTarget1
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,262 @@
+Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
+PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
+Unable to load player prefs
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+ALSA lib confmisc.c:767:(parse_card) cannot find card '0'
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
+ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5220:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2642:(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:767:(parse_card) cannot find card '0'
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
+ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5220:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2642:(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  0.086 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: 0.863237 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]: 5923 frames, [16.0 KB-32.0 KB]: 100 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 44
+    [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]: 6024 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 6.9 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 6024 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.7 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]: 4692 frames, [64.0 KB-128.0 KB]: 1332 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]: 6024 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]: 6024 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]: 6023 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]: 6024 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]: 6024 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": 1.0280466079711914,
+            "min": 1.0110224485397339,
+            "max": 2.8750667572021484,
+            "count": 22
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 10596.076171875,
+            "min": 9779.2509765625,
+            "max": 29443.55859375,
+            "count": 22
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 219992.0,
+            "min": 9952.0,
+            "max": 219992.0,
+            "count": 22
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 219992.0,
+            "min": 9952.0,
+            "max": 219992.0,
+            "count": 22
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 12.157833099365234,
+            "min": 0.45086419582366943,
+            "max": 12.157833099365234,
+            "count": 22
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2480.197998046875,
+            "min": 87.4676513671875,
+            "max": 2480.197998046875,
+            "count": 22
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 22
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 10945.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 22
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06965578150457255,
+            "min": 0.05857227130571332,
+            "max": 0.07422991613751875,
+            "count": 22
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.3482789075228627,
+            "min": 0.2616743308380155,
+            "max": 0.3512510006380491,
+            "count": 22
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.19005702956050047,
+            "min": 0.12550333928540533,
+            "max": 0.2836234310678407,
+            "count": 22
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.9502851478025024,
+            "min": 0.5020133571416213,
+            "max": 1.4181171553392036,
+            "count": 22
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 6.120097959999993e-06,
+            "min": 6.120097959999993e-06,
+            "max": 0.00029262000246,
+            "count": 22
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 3.060048979999996e-05,
+            "min": 3.060048979999996e-05,
+            "max": 0.0013956000348,
+            "count": 22
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10203999999999999,
+            "min": 0.10203999999999999,
+            "max": 0.19754000000000002,
+            "count": 22
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.5102,
+            "min": 0.44616,
+            "max": 0.9652000000000002,
+            "count": 22
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.00011179599999999988,
+            "min": 0.00011179599999999988,
+            "max": 0.004877246,
+            "count": 22
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0005589799999999994,
+            "min": 0.0005589799999999994,
+            "max": 0.023263480000000003,
+            "count": 22
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 23.90740740740741,
+            "min": 3.522727272727273,
+            "max": 23.90740740740741,
+            "count": 22
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1291.0,
+            "min": 155.0,
+            "max": 1306.0,
+            "count": 22
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 23.90740740740741,
+            "min": 3.522727272727273,
+            "max": 23.90740740740741,
+            "count": 22
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1291.0,
+            "min": 155.0,
+            "max": 1306.0,
+            "count": 22
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 22
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 22
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1680251070",
+        "python_version": "3.9.16 (main, Dec  7 2022, 01:11:51) \n[GCC 9.4.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.11.0+cu102",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1680251596"
+    },
+    "total": 526.217956899,
+    "count": 1,
+    "self": 0.4328350230000524,
+    "children": {
+        "run_training.setup": {
+            "total": 0.10668283199993311,
+            "count": 1,
+            "self": 0.10668283199993311
+        },
+        "TrainerController.start_learning": {
+            "total": 525.678439044,
+            "count": 1,
+            "self": 0.6686095250202015,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 3.815780942999936,
+                    "count": 1,
+                    "self": 3.815780942999936
+                },
+                "TrainerController.advance": {
+                    "total": 521.0643722089801,
+                    "count": 20078,
+                    "self": 0.3087317190054364,
+                    "children": {
+                        "env_step": {
+                            "total": 520.7556404899747,
+                            "count": 20078,
+                            "self": 380.98278943394484,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 139.45396463198676,
+                                    "count": 20078,
+                                    "self": 2.0112132909926004,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 137.44275134099416,
+                                            "count": 20078,
+                                            "self": 137.44275134099416
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.31888642404305756,
+                                    "count": 20078,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 524.0173960119766,
+                                            "count": 20078,
+                                            "is_parallel": true,
+                                            "self": 241.7524279499478,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0054838219998600835,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.003928708000103143,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0015551139997569408,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0015551139997569408
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.05364512999994986,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006299010001384886,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0010993900000357826,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0010993900000357826
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.05002382299994679,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.05002382299994679
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0018920159998288,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003920489996289689,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.001499967000199831,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.001499967000199831
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 282.26496806202886,
+                                                    "count": 20077,
+                                                    "is_parallel": true,
+                                                    "self": 11.165753185946414,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 6.429724858024429,
+                                                            "count": 20077,
+                                                            "is_parallel": true,
+                                                            "self": 6.429724858024429
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 227.72859026403103,
+                                                            "count": 20077,
+                                                            "is_parallel": true,
+                                                            "self": 227.72859026403103
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 36.94089975402699,
+                                                            "count": 20077,
+                                                            "is_parallel": true,
+                                                            "self": 7.508476882952436,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 29.43242287107455,
+                                                                    "count": 200770,
+                                                                    "is_parallel": true,
+                                                                    "self": 29.43242287107455
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.00037947700002405327,
+                    "count": 1,
+                    "self": 0.00037947700002405327,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 517.1657587470763,
+                                    "count": 466170,
+                                    "is_parallel": true,
+                                    "self": 11.511085281968917,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 286.6370546651078,
+                                            "count": 466170,
+                                            "is_parallel": true,
+                                            "self": 283.1785471871085,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 3.4585074779993192,
+                                                    "count": 11,
+                                                    "is_parallel": true,
+                                                    "self": 3.4585074779993192
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 219.01761879999958,
+                                            "count": 100,
+                                            "is_parallel": true,
+                                            "self": 81.01951349499427,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 137.9981053050053,
+                                                    "count": 5097,
+                                                    "is_parallel": true,
+                                                    "self": 137.9981053050053
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.12929688999975042,
+                    "count": 1,
+                    "self": 0.0010133709997717233,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.1282835189999787,
+                            "count": 1,
+                            "self": 0.1282835189999787
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 59976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-59976.onnx",
+                "reward": 14.363636363636363,
+                "creation_time": 1680251218.9340916,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-59976.pt"
+                ]
+            },
+            {
+                "steps": 79968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-79968.onnx",
+                "reward": 17.545454545454547,
+                "creation_time": 1680251265.8045092,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-79968.pt"
+                ]
+            },
+            {
+                "steps": 99960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 20.09090909090909,
+                "creation_time": 1680251311.858378,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                ]
+            },
+            {
+                "steps": 119952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-119952.onnx",
+                "reward": 21.545454545454547,
+                "creation_time": 1680251358.9905791,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-119952.pt"
+                ]
+            },
+            {
+                "steps": 139944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-139944.onnx",
+                "reward": 23.0,
+                "creation_time": 1680251405.3778043,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-139944.pt"
+                ]
+            },
+            {
+                "steps": 159936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-159936.onnx",
+                "reward": 23.545454545454547,
+                "creation_time": 1680251452.602634,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-159936.pt"
+                ]
+            },
+            {
+                "steps": 179992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-179992.onnx",
+                "reward": 23.0,
+                "creation_time": 1680251498.4984195,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-179992.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 24.727272727272727,
+                "creation_time": 1680251544.6864035,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 219992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-219992.onnx",
+                "reward": 24.3,
+                "creation_time": 1680251595.9174867,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-219992.pt"
+                ]
+            },
+            {
+                "steps": 220576,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-220576.onnx",
+                "reward": 24.272727272727273,
+                "creation_time": 1680251596.1108925,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-220576.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 220576,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 24.272727272727273,
+            "creation_time": 1680251596.1108925,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-220576.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}