First Push

README.md

@@ -0,0 +1,35 @@
+---
+library_name: ml-agents
+tags:
+- SnowballTarget
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-SnowballTarget
+---
+
+  # **ppo** Agent playing **SnowballTarget**
+  This is a trained model of a **ppo** agent playing **SnowballTarget**
+  using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
+
+  ## Usage (with ML-Agents)
+  The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
+
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+  - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
+  browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
+  - A *longer tutorial* to understand how works ML-Agents:
+  https://huggingface.co/learn/deep-rl-course/unit5/introduction
+
+  ### Resume the training
+  ```bash
+  mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
+  ```
+
+  ### Watch your Agent play
+  You can watch your agent **playing directly in your browser**
+
+  1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
+  2. Step 1: Find your model_id: osmancanyuca/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:c6b368200b8c7fee1be9c1eaf6e61131149588ab22d0b713d749e2f62bc74b94
+size 646532

SnowballTarget/SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84a6677595403b7990802f32c4e3ad0a8563f626b8286cbf86a428e666f8be37
+size 646532

SnowballTarget/SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:778e37088ddcf79f94a4b0654fd226534074e0ad911d00f9ce135dfcba99f699
+size 3843968

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca5215c6c080d291feb9c6799d38bb4bc2c1693985b153c7f8e319532ea15ed2
+size 646532

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2e7447908384d3c56061dd2216d6148d967823f8e993516ead6c18ac4e18e8a
+size 3843968

SnowballTarget/SnowballTarget-200112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca5215c6c080d291feb9c6799d38bb4bc2c1693985b153c7f8e319532ea15ed2
+size 646532

SnowballTarget/SnowballTarget-200112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:205d6f949281b0b87dea69c5b728981d25309f8f41ee75eda4b19e710dc6172a
+size 3843968

SnowballTarget/SnowballTarget-249984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35f9b7ed9c045fbc8b986f3ae580138e742ce7d0ca4a2b2fc304abca1e0b7887
+size 646532

SnowballTarget/SnowballTarget-249984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7123a7483499367a87ca616e35bbeb9eccd4382b3873c6c09e3b6d0314ff82a
+size 3843968

SnowballTarget/SnowballTarget-299944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f7d7de1ef6a633e137c98d06fea3ce21887919bfde2c729c3db2485e7fcd482
+size 646532

SnowballTarget/SnowballTarget-299944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53f14000f4eb5d96bed77d110749576e527f2a61b4f4e4b0464726120ee5e586
+size 3843968

SnowballTarget/SnowballTarget-349968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:547edb22cf9255bfca8a6b99ac0d02f4bc2a5b64e658964676d445458d95dbac
+size 646532

SnowballTarget/SnowballTarget-349968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbc3171c82723609ee64390e06337297833191ab39d56b5939c1c6f8702704b2
+size 3843968

SnowballTarget/SnowballTarget-399968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51eddc7f22ef9fb0341feb879a6bc8519ed1994c41cb05191925c34e78882c3f
+size 646532

SnowballTarget/SnowballTarget-399968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59b8cab7373fa7e6d788bbbf9faf1d1c6861820d7e8628e631ad79b10b2705d5
+size 3843968

SnowballTarget/SnowballTarget-449992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a16b7445044c92310a794280ec6720cb7fb8f3ab8407addb76aaa3f66d2e539b
+size 646532

SnowballTarget/SnowballTarget-449992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39fae7a0ab481fdff39d62a298bfb27bef2be2a3f969662a82fcf4c50c9902f2
+size 3843968

SnowballTarget/SnowballTarget-499952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6b368200b8c7fee1be9c1eaf6e61131149588ab22d0b713d749e2f62bc74b94
+size 646532

SnowballTarget/SnowballTarget-499952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e31cfff2c9ecbbbaa7e35f1b45f6198c6bce46456b7737d73e67895580bcd679
+size 3843968

SnowballTarget/SnowballTarget-500016.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6b368200b8c7fee1be9c1eaf6e61131149588ab22d0b713d749e2f62bc74b94
+size 646532

SnowballTarget/SnowballTarget-500016.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ec70361e0c19d32caa430601219818986ece93339be046809b3d892d385b18b
+size 3843968

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ec70361e0c19d32caa430601219818986ece93339be046809b3d892d385b18b
+size 3843968

SnowballTarget/events.out.tfevents.1690889854.7123b5f7e039.1282.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:450c1659f534e08cdaef3816de87a94fcb6dce3b0be89e6d143c1aa58a6bf38a
+size 28555

SnowballTarget/events.out.tfevents.1690890344.7123b5f7e039.3435.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f49333532652d2f5dad249eafd627bf52e6b80264f552212c06b8edbede8197c
+size 25646

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": 500000, "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: 500000
+    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:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+FMOD initialized on nosound output
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.084 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: 0.624853 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]: 8047 frames, [16.0 KB-32.0 KB]: 136 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.0 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 198 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 304.0 KB
+      Peak Allocated Bytes 228.9 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 36
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 8184 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 7.5 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 8184 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]: 7926 frames, [64.0 KB-128.0 KB]: 258 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]: 8184 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]: 8184 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]: 8183 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]: 8184 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]: 8184 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": 0.49389326572418213,
+            "min": 0.48974916338920593,
+            "max": 0.8311858773231506,
+            "count": 30
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 4780.88671875,
+            "min": 4665.3505859375,
+            "max": 8503.03125,
+            "count": 30
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 499952.0,
+            "min": 209936.0,
+            "max": 499952.0,
+            "count": 30
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 499952.0,
+            "min": 209936.0,
+            "max": 499952.0,
+            "count": 30
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 13.264318466186523,
+            "min": 12.78330135345459,
+            "max": 13.550152778625488,
+            "count": 30
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2705.9208984375,
+            "min": 2454.393798828125,
+            "max": 2754.96923828125,
+            "count": 30
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 30
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 10945.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 30
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06444381270489162,
+            "min": 0.06138828125846225,
+            "max": 0.07410374682605798,
+            "count": 30
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.3222190635244581,
+            "min": 0.245553125033849,
+            "max": 0.35996163713257284,
+            "count": 30
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.16523896856050865,
+            "min": 0.16523896856050865,
+            "max": 0.20906220627766028,
+            "count": 30
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.8261948428025433,
+            "min": 0.6695908378152287,
+            "max": 1.0453110313883014,
+            "count": 30
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 3.1056989647999945e-06,
+            "min": 3.1056989647999945e-06,
+            "max": 0.00017668564110480002,
+            "count": 30
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 1.5528494823999972e-05,
+            "min": 1.5528494823999972e-05,
+            "max": 0.000853728215424,
+            "count": 30
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10103520000000002,
+            "min": 0.10103520000000002,
+            "max": 0.15889520000000001,
+            "count": 30
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.5051760000000001,
+            "min": 0.4120608,
+            "max": 0.7845760000000002,
+            "count": 30
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 6.165647999999992e-05,
+            "min": 6.165647999999992e-05,
+            "max": 0.002948870480000001,
+            "count": 30
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0003082823999999996,
+            "min": 0.0003082823999999996,
+            "max": 0.0142503424,
+            "count": 30
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 26.054545454545455,
+            "min": 25.01818181818182,
+            "max": 27.045454545454547,
+            "count": 30
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1433.0,
+            "min": 1106.0,
+            "max": 1460.0,
+            "count": 30
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 26.054545454545455,
+            "min": 25.01818181818182,
+            "max": 27.045454545454547,
+            "count": 30
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1433.0,
+            "min": 1106.0,
+            "max": 1460.0,
+            "count": 30
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 30
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 30
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1690890343",
+        "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
+        "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": "1690891037"
+    },
+    "total": 694.623827245,
+    "count": 1,
+    "self": 0.43983715800004575,
+    "children": {
+        "run_training.setup": {
+            "total": 0.0312753050000083,
+            "count": 1,
+            "self": 0.0312753050000083
+        },
+        "TrainerController.start_learning": {
+            "total": 694.152714782,
+            "count": 1,
+            "self": 0.7819660919807347,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 3.913775874999942,
+                    "count": 1,
+                    "self": 3.913775874999942
+                },
+                "TrainerController.advance": {
+                    "total": 689.3154025650192,
+                    "count": 27279,
+                    "self": 0.37225476100275046,
+                    "children": {
+                        "env_step": {
+                            "total": 688.9431478040165,
+                            "count": 27279,
+                            "self": 502.8756942400214,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 185.61299342100756,
+                                    "count": 27279,
+                                    "self": 2.58825859700994,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 183.02473482399762,
+                                            "count": 27279,
+                                            "self": 183.02473482399762
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.45446014298750015,
+                                    "count": 27279,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 691.9716259699957,
+                                            "count": 27279,
+                                            "is_parallel": true,
+                                            "self": 327.18913087799194,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0018565589999752774,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.000559727999984716,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0012968309999905614,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0012968309999905614
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.03499106699996446,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006187319999071406,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0004812870000705516,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004812870000705516
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.0318589549999615,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0318589549999615
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.00203209300002527,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00048141700005999155,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0015506759999652786,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0015506759999652786
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 364.7824950920037,
+                                                    "count": 27278,
+                                                    "is_parallel": true,
+                                                    "self": 15.603054116971748,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 7.835772952041566,
+                                                            "count": 27278,
+                                                            "is_parallel": true,
+                                                            "self": 7.835772952041566
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 290.0039097430006,
+                                                            "count": 27278,
+                                                            "is_parallel": true,
+                                                            "self": 290.0039097430006
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 51.33975827998984,
+                                                            "count": 27278,
+                                                            "is_parallel": true,
+                                                            "self": 9.260755715980281,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 42.079002564009556,
+                                                                    "count": 272780,
+                                                                    "is_parallel": true,
+                                                                    "self": 42.079002564009556
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.00010633400006554439,
+                    "count": 1,
+                    "self": 0.00010633400006554439,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 684.0919438569363,
+                                    "count": 623524,
+                                    "is_parallel": true,
+                                    "self": 13.70914407186956,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 367.81647221106573,
+                                            "count": 623524,
+                                            "is_parallel": true,
+                                            "self": 366.1795820880658,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 1.6368901229999437,
+                                                    "count": 6,
+                                                    "is_parallel": true,
+                                                    "self": 1.6368901229999437
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 302.566327574001,
+                                            "count": 136,
+                                            "is_parallel": true,
+                                            "self": 122.20453180500476,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 180.36179576899622,
+                                                    "count": 6930,
+                                                    "is_parallel": true,
+                                                    "self": 180.36179576899622
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.14146391600002062,
+                    "count": 1,
+                    "self": 0.0010155050001685595,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.14044841099985206,
+                            "count": 1,
+                            "self": 0.14044841099985206
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 149984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 22.90909090909091,
+                "creation_time": 1690890202.6211483,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 24.90909090909091,
+                "creation_time": 1690890317.6469834,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 200112,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 24.90909090909091,
+                "creation_time": 1690890317.8116348,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                ]
+            },
+            {
+                "steps": 249984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.onnx",
+                "reward": 25.545454545454547,
+                "creation_time": 1690890462.0969536,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.pt"
+                ]
+            },
+            {
+                "steps": 299944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299944.onnx",
+                "reward": 25.454545454545453,
+                "creation_time": 1690890576.445724,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-299944.pt"
+                ]
+            },
+            {
+                "steps": 349968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349968.onnx",
+                "reward": 27.09090909090909,
+                "creation_time": 1690890692.7718558,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-349968.pt"
+                ]
+            },
+            {
+                "steps": 399968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.onnx",
+                "reward": 25.272727272727273,
+                "creation_time": 1690890806.5998008,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.pt"
+                ]
+            },
+            {
+                "steps": 449992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449992.onnx",
+                "reward": 27.727272727272727,
+                "creation_time": 1690890922.4949217,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-449992.pt"
+                ]
+            },
+            {
+                "steps": 499952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499952.onnx",
+                "reward": 25.272727272727273,
+                "creation_time": 1690891037.270085,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-499952.pt"
+                ]
+            },
+            {
+                "steps": 500016,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-500016.onnx",
+                "reward": 25.272727272727273,
+                "creation_time": 1690891037.4329965,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-500016.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 500016,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 25.272727272727273,
+            "creation_time": 1690891037.4329965,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-500016.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}