First!

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: yumingyi/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 sha256:2b72e9e02057b3786fb28f7da9237cce8c88057cf81d17413367b49f34dd635d
+size 646532

SnowballTarget/SnowballTarget-319960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2ce011698635026cf9e84104220232207b2a6c240575fa46e49e241618b2ccf
+size 646532

SnowballTarget/SnowballTarget-319960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1ce59e01a12e9585d2051da9b13dd38cd8311fc046bbea4845f9934780c953f
+size 3843968

SnowballTarget/SnowballTarget-329992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2186a1dc6ce3650cbc6c165974a6b8220498b363275c6774157ac003e4ed149a
+size 646532

SnowballTarget/SnowballTarget-329992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fc5060952147fce3bff935b9d6d966c651fddeae1e59e84c8de3d1393f3553c
+size 3843968

SnowballTarget/SnowballTarget-339952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:954cd5d01d8409b67375394edcb1bd73b6f93deb928e29e5208e412889ccc519
+size 646532

SnowballTarget/SnowballTarget-339952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b883d2a49993a7eb74ef06118544c903f884710b3595a5f3af04f0d8e50f14a1
+size 3843968

SnowballTarget/SnowballTarget-349992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:132d4d31af3c9938f2ba2b4458f1962954cf69dce1f4559e6c5f7254fcbd7a27
+size 646532

SnowballTarget/SnowballTarget-349992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c02350f046023f877c29b6c9f29b81b9296b99e432b32327c5cf891c35d5eeb
+size 3843968

SnowballTarget/SnowballTarget-359944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f322f1f3dc1b344bbdd7a11c1f2ae67e77257cdf0a831d93582f655b7eb0face
+size 646532

SnowballTarget/SnowballTarget-359944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98d4ed9ee235e277cecfe3dbcde06e6f750e6fcb2d307677557bf31f4def1d94
+size 3843968

SnowballTarget/SnowballTarget-369984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f989785a212f3ae90cec53560fa7295accfe13bfef4333f6188bcbbf55202e1
+size 646532

SnowballTarget/SnowballTarget-369984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7356fbfeb268fbba36c8a13f1231543916b7d2b05d38daef6a725ae4bf59d9fa
+size 3843968

SnowballTarget/SnowballTarget-379936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c22b02f84294d928a76892e2a0ea4256d2a49b9b016c57786901f1fd67e72c1
+size 646532

SnowballTarget/SnowballTarget-379936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54c571ca199c6497aae992cb834a52c50ecd584286fd2d1481f79d91007cd3e1
+size 3843968

SnowballTarget/SnowballTarget-389976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d34060f4f08663a58867fe33a52e5a0b115f2c2ddc0a7313b971f157cb040ee
+size 646532

SnowballTarget/SnowballTarget-389976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e9e1ebe963ef14cbb4286350f4afcae726d8d1fd484e10e0167332d9e4ec734
+size 3843968

SnowballTarget/SnowballTarget-399992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b72e9e02057b3786fb28f7da9237cce8c88057cf81d17413367b49f34dd635d
+size 646532

SnowballTarget/SnowballTarget-399992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce64763954e15c219d915ffdcbc41cc69fe280f55640e9fa9e3ef9c66c3d881e
+size 3843968

SnowballTarget/SnowballTarget-400312.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b72e9e02057b3786fb28f7da9237cce8c88057cf81d17413367b49f34dd635d
+size 646532

SnowballTarget/SnowballTarget-400312.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aed9ab0a6c792899baa59ad2b951d5e068e88b1abf4529f1947254d0b73720d0
+size 3843968

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aed9ab0a6c792899baa59ad2b951d5e068e88b1abf4529f1947254d0b73720d0
+size 3843968

SnowballTarget/events.out.tfevents.1680016098.3c70acfe213f.2146.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26e1b02966c0aae534d2afe6b06a73d6656eb33263d4685a3c9880a47273a846
+size 39948

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": 10000, "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, "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: 10000
+    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
+  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  0.082 seconds
+ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+UnloadTime: 0.650672 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]: 10742 frames, [16.0 KB-32.0 KB]: 182 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 41
+    [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]: 10923 frames, [8.0 MB-16.0 MB]: 2 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 8.9 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 10925 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]: 10009 frames, [64.0 KB-128.0 KB]: 916 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 66.8 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 10925 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]: 10925 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]: 10924 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]: 10925 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]: 10925 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": 0.7092481255531311,
+            "min": 0.6914249062538147,
+            "max": 2.859597682952881,
+            "count": 40
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 7216.599609375,
+            "min": 6670.17626953125,
+            "max": 29253.68359375,
+            "count": 40
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 399992.0,
+            "min": 9952.0,
+            "max": 399992.0,
+            "count": 40
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 399992.0,
+            "min": 9952.0,
+            "max": 399992.0,
+            "count": 40
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 13.60815143585205,
+            "min": 0.5177081227302551,
+            "max": 13.718135833740234,
+            "count": 40
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2653.589599609375,
+            "min": 100.43537139892578,
+            "max": 2805.37451171875,
+            "count": 40
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 40
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 8756.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 40
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.0768792116551755,
+            "min": 0.06191642284279177,
+            "max": 0.07718766891733085,
+            "count": 40
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.307516846620702,
+            "min": 0.25649684770706144,
+            "max": 0.3731950204773788,
+            "count": 40
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.203520383101468,
+            "min": 0.126542127057773,
+            "max": 0.2933554678570991,
+            "count": 40
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.814081532405872,
+            "min": 0.506168508231092,
+            "max": 1.2733594412897147,
+            "count": 40
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 3.891098702999994e-06,
+            "min": 3.891098702999994e-06,
+            "max": 0.000295941001353,
+            "count": 40
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 1.5564394811999976e-05,
+            "min": 1.5564394811999976e-05,
+            "max": 0.0014425800191399996,
+            "count": 40
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.101297,
+            "min": 0.101297,
+            "max": 0.19864700000000002,
+            "count": 40
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.405188,
+            "min": 0.405188,
+            "max": 0.98086,
+            "count": 40
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 7.472029999999992e-05,
+            "min": 7.472029999999992e-05,
+            "max": 0.004932485299999999,
+            "count": 40
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.00029888119999999966,
+            "min": 0.00029888119999999966,
+            "max": 0.024044914,
+            "count": 40
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 26.613636363636363,
+            "min": 3.7954545454545454,
+            "max": 26.954545454545453,
+            "count": 40
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1171.0,
+            "min": 167.0,
+            "max": 1482.0,
+            "count": 40
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 26.613636363636363,
+            "min": 3.7954545454545454,
+            "max": 26.954545454545453,
+            "count": 40
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1171.0,
+            "min": 167.0,
+            "max": 1482.0,
+            "count": 40
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 40
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 40
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1680016092",
+        "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": "1680017007"
+    },
+    "total": 915.4806048120001,
+    "count": 1,
+    "self": 0.7804635680000729,
+    "children": {
+        "run_training.setup": {
+            "total": 0.1130621949999977,
+            "count": 1,
+            "self": 0.1130621949999977
+        },
+        "TrainerController.start_learning": {
+            "total": 914.5870790490001,
+            "count": 1,
+            "self": 1.0963760829977218,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 10.177959025999996,
+                    "count": 1,
+                    "self": 10.177959025999996
+                },
+                "TrainerController.advance": {
+                    "total": 903.1029277260022,
+                    "count": 36414,
+                    "self": 0.5579183590085677,
+                    "children": {
+                        "env_step": {
+                            "total": 902.5450093669937,
+                            "count": 36414,
+                            "self": 653.1010794930276,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 248.9254561209683,
+                                    "count": 36414,
+                                    "self": 3.8669713699611634,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 245.05848475100714,
+                                            "count": 36414,
+                                            "self": 245.05848475100714
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.5184737529978065,
+                                    "count": 36414,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 911.6279454920107,
+                                            "count": 36414,
+                                            "is_parallel": true,
+                                            "self": 433.6956312819878,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.006304095000018606,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0043291879999856064,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0019749070000329993,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0019749070000329993
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.08969511200001534,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005922080000004826,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00044667899999240035,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00044667899999240035
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.08681415600000264,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.08681415600000264
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0018420690000198192,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003875090000065029,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0014545600000133163,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0014545600000133163
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 477.93231421002287,
+                                                    "count": 36413,
+                                                    "is_parallel": true,
+                                                    "self": 18.9226054440349,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 10.234040669987394,
+                                                            "count": 36413,
+                                                            "is_parallel": true,
+                                                            "self": 10.234040669987394
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 387.5469674680029,
+                                                            "count": 36413,
+                                                            "is_parallel": true,
+                                                            "self": 387.5469674680029
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 61.22870062799768,
+                                                            "count": 36413,
+                                                            "is_parallel": true,
+                                                            "self": 12.181203025999196,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 49.04749760199849,
+                                                                    "count": 364130,
+                                                                    "is_parallel": true,
+                                                                    "self": 49.04749760199849
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.00022863499998493353,
+                    "count": 1,
+                    "self": 0.00022863499998493353,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 896.866285206891,
+                                    "count": 766448,
+                                    "is_parallel": true,
+                                    "self": 18.411496065994015,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 497.5298746208978,
+                                            "count": 766448,
+                                            "is_parallel": true,
+                                            "self": 486.34885421489827,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 11.181020405999504,
+                                                    "count": 40,
+                                                    "is_parallel": true,
+                                                    "self": 11.181020405999504
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 380.9249145199993,
+                                            "count": 181,
+                                            "is_parallel": true,
+                                            "self": 146.5094337030053,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 234.41548081699398,
+                                                    "count": 9225,
+                                                    "is_parallel": true,
+                                                    "self": 234.41548081699398
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.20958757900007186,
+                    "count": 1,
+                    "self": 0.0013426230000277428,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.2082449560000441,
+                            "count": 1,
+                            "self": 0.2082449560000441
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 319960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-319960.onnx",
+                "reward": 27.0,
+                "creation_time": 1680016825.4571738,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-319960.pt"
+                ]
+            },
+            {
+                "steps": 329992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-329992.onnx",
+                "reward": 25.9,
+                "creation_time": 1680016850.52401,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-329992.pt"
+                ]
+            },
+            {
+                "steps": 339952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-339952.onnx",
+                "reward": 27.272727272727273,
+                "creation_time": 1680016872.0484772,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-339952.pt"
+                ]
+            },
+            {
+                "steps": 349992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.onnx",
+                "reward": 27.0,
+                "creation_time": 1680016895.3343413,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.pt"
+                ]
+            },
+            {
+                "steps": 359944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-359944.onnx",
+                "reward": 26.636363636363637,
+                "creation_time": 1680016916.5616581,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-359944.pt"
+                ]
+            },
+            {
+                "steps": 369984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-369984.onnx",
+                "reward": 26.363636363636363,
+                "creation_time": 1680016939.9756908,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-369984.pt"
+                ]
+            },
+            {
+                "steps": 379936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-379936.onnx",
+                "reward": 27.09090909090909,
+                "creation_time": 1680016962.4009147,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-379936.pt"
+                ]
+            },
+            {
+                "steps": 389976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-389976.onnx",
+                "reward": 26.818181818181817,
+                "creation_time": 1680016984.247752,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-389976.pt"
+                ]
+            },
+            {
+                "steps": 399992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.onnx",
+                "reward": 27.09090909090909,
+                "creation_time": 1680017006.495965,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.pt"
+                ]
+            },
+            {
+                "steps": 400312,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-400312.onnx",
+                "reward": 27.09090909090909,
+                "creation_time": 1680017006.760535,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-400312.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 400312,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 27.09090909090909,
+            "creation_time": 1680017006.760535,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-400312.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}