Second 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: tux/ppo-SnowballTarget2
+  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 sha256:0eb32c4466e2e06c75fab8f8173c2785bde57043bd64d122cd82c03cb86b0986
+size 646532

SnowballTarget/SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:998fbb1dec12821033018b56a4775726b53816ddd50d115fce1fd6ff412bd4fc
+size 646532

SnowballTarget/SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2115d6d4668361dea6afeb7aa65b6ecd84e1d11fb30a6da975e21047d4b84fb7
+size 5119318

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68ac1f76ebb5468be255d6b39ae561558208fb4ea7fbd41015f6fc18ef2281fa
+size 646532

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32598db4970a0012615097e8876246c641eca94570c024a99d2da4d72169b96f
+size 5119318

SnowballTarget/SnowballTarget-200112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68ac1f76ebb5468be255d6b39ae561558208fb4ea7fbd41015f6fc18ef2281fa
+size 646532

SnowballTarget/SnowballTarget-200112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c992b5de834fe7f857ef719ce9a24ebaae5f81004b362f029602bdf2d6dbc986
+size 5119318

SnowballTarget/SnowballTarget-249984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8bcb9d9dd2af3c677d3e189b7057a91f9554db598e29c429f7e137a85ac01e8
+size 646532

SnowballTarget/SnowballTarget-249984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d70e49f2585a3b88a7fa6585c37b670fdbbdc5f7d5388736edd9a1c1273ff60
+size 5119318

SnowballTarget/SnowballTarget-270424.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fef3afeb968695118cec5daed8c53290eacefcd9925eb09c52bdc777b214490
+size 646532

SnowballTarget/SnowballTarget-270424.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f13c6ce49b94ff0f4b36245098fc34f1488f87efeac3c21105509c3e3dfc335
+size 5119318

SnowballTarget/SnowballTarget-299984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b945a299d61e3b88e0eee4edd6648dd2c6e5c145cefbecb6458d4f2d27515d3
+size 646532

SnowballTarget/SnowballTarget-299984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b21d1aa93d751595b62e6ac3e981efab6ac427da96ce6c09ba05be653b14a66
+size 3843968

SnowballTarget/SnowballTarget-349944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44a42f4520cd487abb584938358183eda3fbf4d633789f728bc477d3f3f00a94
+size 646532

SnowballTarget/SnowballTarget-349944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6d23b91bdd5138b851b2b2d778c23e54c7679ffb56c1b5dc12b4a9b15f02be3
+size 3843968

SnowballTarget/SnowballTarget-399944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eb32c4466e2e06c75fab8f8173c2785bde57043bd64d122cd82c03cb86b0986
+size 646532

SnowballTarget/SnowballTarget-399944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74dfe5ac4424f5c01efe4bca96bd4ae15bb2f5766fabc510d0387a8b145a3831
+size 3843968

SnowballTarget/SnowballTarget-400136.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eb32c4466e2e06c75fab8f8173c2785bde57043bd64d122cd82c03cb86b0986
+size 646532

SnowballTarget/SnowballTarget-400136.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52958a0b24c1b0b79a881d37d9c3e1978bf5c97e621918b046d3c3c05d355177
+size 3843968

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52958a0b24c1b0b79a881d37d9c3e1978bf5c97e621918b046d3c3c05d355177
+size 3843968

SnowballTarget/events.out.tfevents.1687085600.0fd2ca80588f.1742.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e004273ecabcd931ce2f967c23ebc2667d7c33409a62be05b2499e0d92d97223
+size 42727

SnowballTarget/events.out.tfevents.1687088968.0fd2ca80588f.15680.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29fd721797ab83047eb8661289c6eed4891a80800698a49e9356755b57cedad5
+size 1421

SnowballTarget/events.out.tfevents.1687089009.0fd2ca80588f.15910.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25a29002962dd1892da66094e33f513585d85467702a4ce0dff461a9b7b15b12
+size 8558

SnowballTarget/events.out.tfevents.1687089214.0fd2ca80588f.16826.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a80e3f3a2b5a8b313d0b0b4ec8db18c377536895b1213dec0d61536948bdcba8
+size 11816

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 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": true, "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: 50000
+    network_settings:
+      normalize: false
+      hidden_units: 256
+      num_layers: 2
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+    init_path: null
+    keep_checkpoints: 10
+    even_checkpoints: false
+    max_steps: 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: 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: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  0.127 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: 0.837779 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]: 3487 frames, [16.0 KB-32.0 KB]: 59 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 34
+    [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]: 3547 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 6.1 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 3547 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]: 3441 frames, [64.0 KB-128.0 KB]: 106 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]: 3547 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]: 3547 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]: 3546 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]: 3547 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]: 3547 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": 0.6749759912490845,
+            "min": 0.6749759912490845,
+            "max": 0.8381103873252869,
+            "count": 13
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 6459.5205078125,
+            "min": 6459.5205078125,
+            "max": 8555.4306640625,
+            "count": 13
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 399944.0,
+            "min": 279992.0,
+            "max": 399944.0,
+            "count": 13
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 399944.0,
+            "min": 279992.0,
+            "max": 399944.0,
+            "count": 13
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 12.998022079467773,
+            "min": 12.612207412719727,
+            "max": 13.121735572814941,
+            "count": 13
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2521.6162109375,
+            "min": 2397.19091796875,
+            "max": 2676.833984375,
+            "count": 13
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 13
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 8756.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 13
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06842379256248059,
+            "min": 0.06274938085330445,
+            "max": 0.07379341599087497,
+            "count": 13
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.27369517024992235,
+            "min": 0.2530691640870417,
+            "max": 0.36896707995437483,
+            "count": 13
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.19016173211675066,
+            "min": 0.18351931782329783,
+            "max": 0.2117971901800118,
+            "count": 13
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.7606469284670027,
+            "min": 0.7515429112256742,
+            "max": 1.058985950900059,
+            "count": 13
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 4.0230986590000025e-06,
+            "min": 4.0230986590000025e-06,
+            "max": 9.312306895899999e-05,
+            "count": 13
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 1.609239463600001e-05,
+            "min": 1.609239463600001e-05,
+            "max": 0.0003954903681699999,
+            "count": 13
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10134100000000001,
+            "min": 0.10134100000000001,
+            "max": 0.13104100000000002,
+            "count": 13
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.40536400000000006,
+            "min": 0.40536400000000006,
+            "max": 0.63183,
+            "count": 13
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 7.691590000000003e-05,
+            "min": 7.691590000000003e-05,
+            "max": 0.0015589459000000005,
+            "count": 13
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0003076636000000001,
+            "min": 0.0003076636000000001,
+            "max": 0.006628317,
+            "count": 13
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 25.681818181818183,
+            "min": 24.454545454545453,
+            "max": 26.022727272727273,
+            "count": 13
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1130.0,
+            "min": 1076.0,
+            "max": 1423.0,
+            "count": 13
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 25.681818181818183,
+            "min": 24.454545454545453,
+            "max": 26.022727272727273,
+            "count": 13
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1130.0,
+            "min": 1076.0,
+            "max": 1423.0,
+            "count": 13
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 13
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 13
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1687089213",
+        "python_version": "3.10.12 (main, Jun  7 2023, 12:45:35) [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 --resume",
+        "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": "1687089515"
+    },
+    "total": 302.4342371169996,
+    "count": 1,
+    "self": 0.8387473499997213,
+    "children": {
+        "run_training.setup": {
+            "total": 0.06620121099967946,
+            "count": 1,
+            "self": 0.06620121099967946
+        },
+        "TrainerController.start_learning": {
+            "total": 301.5292885560002,
+            "count": 1,
+            "self": 0.3744299729842169,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 4.302400324000246,
+                    "count": 1,
+                    "self": 4.302400324000246
+                },
+                "TrainerController.advance": {
+                    "total": 296.62832749101517,
+                    "count": 11821,
+                    "self": 0.16391955803783276,
+                    "children": {
+                        "env_step": {
+                            "total": 296.46440793297734,
+                            "count": 11821,
+                            "self": 218.3596087559531,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 77.9404431580283,
+                                    "count": 11821,
+                                    "self": 1.2103973100033727,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 76.73004584802493,
+                                            "count": 11821,
+                                            "self": 76.73004584802493
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.16435601899593166,
+                                    "count": 11821,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 300.37892925197,
+                                            "count": 11821,
+                                            "is_parallel": true,
+                                            "self": 142.82830187891295,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.003400146999865683,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0007431369999721937,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0026570099998934893,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0026570099998934893
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.04434941599993181,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005497960000866442,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00032860099963727407,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00032860099963727407
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.041253743000197574,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.041253743000197574
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0022172760000103153,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004083720004928182,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0018089039995174971,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0018089039995174971
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 157.55062737305707,
+                                                    "count": 11820,
+                                                    "is_parallel": true,
+                                                    "self": 6.540792842022256,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 3.3528731100345794,
+                                                            "count": 11820,
+                                                            "is_parallel": true,
+                                                            "self": 3.3528731100345794
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 125.86504411401711,
+                                                            "count": 11820,
+                                                            "is_parallel": true,
+                                                            "self": 125.86504411401711
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 21.791917306983123,
+                                                            "count": 11820,
+                                                            "is_parallel": true,
+                                                            "self": 3.9140963719200954,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 17.877820935063028,
+                                                                    "count": 118200,
+                                                                    "is_parallel": true,
+                                                                    "self": 17.877820935063028
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.00018013600038102595,
+                    "count": 1,
+                    "self": 0.00018013600038102595,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 294.4034886741424,
+                                    "count": 275822,
+                                    "is_parallel": true,
+                                    "self": 6.150136907125216,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 160.87285804101384,
+                                            "count": 275822,
+                                            "is_parallel": true,
+                                            "self": 159.30715024501342,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 1.5657077960004244,
+                                                    "count": 3,
+                                                    "is_parallel": true,
+                                                    "self": 1.5657077960004244
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 127.38049372600335,
+                                            "count": 58,
+                                            "is_parallel": true,
+                                            "self": 49.78196640102624,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 77.59852732497711,
+                                                    "count": 2955,
+                                                    "is_parallel": true,
+                                                    "self": 77.59852732497711
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.2239506320001965,
+                    "count": 1,
+                    "self": 0.0018281009997735964,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.2221225310004229,
+                            "count": 1,
+                            "self": 0.2221225310004229
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 149984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 22.818181818181817,
+                "creation_time": 1687085979.7950647,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 24.272727272727273,
+                "creation_time": 1687086101.357253,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 200112,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 24.272727272727273,
+                "creation_time": 1687086101.5429204,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                ]
+            },
+            {
+                "steps": 200112,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": null,
+                "creation_time": 1687088971.5190713,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                ]
+            },
+            {
+                "steps": 249984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.onnx",
+                "reward": 23.636363636363637,
+                "creation_time": 1687089134.6237562,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.pt"
+                ]
+            },
+            {
+                "steps": 270424,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-270424.onnx",
+                "reward": null,
+                "creation_time": 1687089187.0483046,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-270424.pt"
+                ]
+            },
+            {
+                "steps": 299984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299984.onnx",
+                "reward": 24.90909090909091,
+                "creation_time": 1687089286.8308792,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-299984.pt"
+                ]
+            },
+            {
+                "steps": 349944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349944.onnx",
+                "reward": 26.454545454545453,
+                "creation_time": 1687089401.55398,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-349944.pt"
+                ]
+            },
+            {
+                "steps": 399944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399944.onnx",
+                "reward": 25.545454545454547,
+                "creation_time": 1687089514.595855,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-399944.pt"
+                ]
+            },
+            {
+                "steps": 400136,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-400136.onnx",
+                "reward": 25.545454545454547,
+                "creation_time": 1687089514.8510673,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-400136.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 400136,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 25.545454545454547,
+            "creation_time": 1687089514.8510673,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-400136.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}