Data

Tools

Indexes

Applications

Experiments

Open Source Science

sb3-contrib

Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code

https://github.com/stable-baselines-team/stable-baselines3-contrib

Science Score: 64.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ✓
    Committers with academic emails
    1 of 31 committers (3.2%) from academic institutions
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (13.9%) to scientific vocabulary

Keywords

experimental gsde gym machine-learning openai pytorch reinforcement-learning reinforcement-learning-algorithms research rl robotics sde stable-baselines

Keywords from Contributors

baselines sb3 toolbox transformer gym-environment gymnasium jax autonomous-driving
Last synced: 6 months ago · JSON representation ·

Repository

Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code

Basic Info
Statistics
  • Stars: 633
  • Watchers: 17
  • Forks: 210
  • Open Issues: 86
  • Releases: 21
Topics
experimental gsde gym machine-learning openai pytorch reinforcement-learning reinforcement-learning-algorithms research rl robotics sde stable-baselines
Created over 5 years ago · Last pushed 6 months ago
Metadata Files
Readme Contributing License Citation

README.md

CI codestyle

Stable-Baselines3 - Contrib (SB3-Contrib)

Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code. "sb3-contrib" for short.

What is SB3-Contrib?

A place for RL algorithms and tools that are considered experimental, e.g. implementations of the latest publications. Goal is to keep the simplicity, documentation and style of stable-baselines3 but for less matured implementations.

Why create this repository?

Over the span of stable-baselines and stable-baselines3, the community has been eager to contribute in form of better logging utilities, environment wrappers, extended support (e.g. different action spaces) and learning algorithms.

However sometimes these utilities were too niche to be considered for stable-baselines or proved to be too difficult to integrate well into the existing code without creating a mess. sb3-contrib aims to fix this by not requiring the neatest code integration with existing code and not setting limits on what is too niche: almost everything remotely useful goes! We hope this allows us to provide reliable implementations following stable-baselines usual standards (consistent style, documentation, etc) beyond the relatively small scope of utilities in the main repository.

Features

See documentation for the full list of included features.

RL Algorithms: - Augmented Random Search (ARS) - Quantile Regression DQN (QR-DQN) - PPO with invalid action masking (MaskablePPO) - PPO with recurrent policy (RecurrentPPO aka PPO LSTM) - Truncated Quantile Critics (TQC) - Trust Region Policy Optimization (TRPO) - Batch Normalization in Deep Reinforcement Learning (CrossQ)

Gym Wrappers: - Time Feature Wrapper

Documentation

Documentation is available online: https://sb3-contrib.readthedocs.io/

Installation

To install Stable Baselines3 contrib with pip, execute:

pip install sb3-contrib

We recommend to use the master version of Stable Baselines3.

To install Stable Baselines3 master version: pip install git+https://github.com/DLR-RM/stable-baselines3

To install Stable Baselines3 contrib master version: pip install git+https://github.com/Stable-Baselines-Team/stable-baselines3-contrib

How To Contribute

If you want to contribute, please read CONTRIBUTING.md guide first.

Citing the Project

To cite this repository in publications (please cite SB3 directly):

bibtex @article{stable-baselines3, author = {Antonin Raffin and Ashley Hill and Adam Gleave and Anssi Kanervisto and Maximilian Ernestus and Noah Dormann}, title = {Stable-Baselines3: Reliable Reinforcement Learning Implementations}, journal = {Journal of Machine Learning Research}, year = {2021}, volume = {22}, number = {268}, pages = {1-8}, url = {http://jmlr.org/papers/v22/20-1364.html} }

Owner

  • Name: Stable-Baselines Team
  • Login: Stable-Baselines-Team
  • Kind: organization

Developement team of the Stable-Baselines project

Citation (CITATION.bib) 

@article{stable-baselines3,
  author  = {Antonin Raffin and Ashley Hill and Adam Gleave and Anssi Kanervisto and Maximilian Ernestus and Noah Dormann},
  title   = {Stable-Baselines3: Reliable Reinforcement Learning Implementations},
  journal = {Journal of Machine Learning Research},
  year    = {2021},
  volume  = {22},
  number  = {268},
  pages   = {1-8},
  url     = {http://jmlr.org/papers/v22/20-1364.html}
}

GitHub Events

Total
  • Create event: 14
  • Release event: 3
  • Issues event: 20
  • Watch event: 142
  • Delete event: 11
  • Issue comment event: 61
  • Push event: 16
  • Pull request review comment event: 4
  • Pull request event: 36
  • Pull request review event: 6
  • Fork event: 31
Last Year
  • Create event: 14
  • Release event: 3
  • Issues event: 20
  • Watch event: 142
  • Delete event: 11
  • Issue comment event: 61
  • Push event: 16
  • Pull request review comment event: 4
  • Pull request event: 36
  • Pull request review event: 6
  • Fork event: 31

Committers

Last synced: 8 months ago

All Time
  • Total Commits: 158
  • Total Committers: 31
  • Avg Commits per committer: 5.097
  • Development Distribution Score (DDS): 0.361
Past Year
  • Commits: 17
  • Committers: 6
  • Avg Commits per committer: 2.833
  • Development Distribution Score (DDS): 0.294
Top Committers
Name Email Commits
Antonin RAFFIN a****n@e****g 101
Quentin Gallouédec 4****c 13
Anssi "Miffyli" Kanervisto k****1@h****m 11
Alex Pasquali a****8@g****m 4
Adam Gleave a****m@g****e 2
Toshiki Watanabe 3****2 2
Armand du Parc Locmaria a****3@g****m 1
Attila Kanto a****o 1
Burak Demirbilek B****b 1
Corentin 1****r 1
Costa Huang c****g@o****m 1
CppMaster p****l@g****m 1
Cyprien c****c@g****m 1
Daniel Palenicek d****n 1
Geoff McDonald g****a@g****m 1
Grégoire Passault g****t@g****m 1
Honglu Fan 6****5 1
Joe Ksiazek h****k@g****m 1
Jonas Reiher 5****r 1
Long M. Lưu (刘明龙) m****3@g****m 1
M. Ernestus m****n@e****e 1
Max Lodel m****l@g****m 1
PatrickHelm 9****m 1
Rogério Júnior r****r@g****m 1
Scott Brownlie s****8@g****m 1
Sean Gillen s****n@u****u 1
Tjeerd Bakker 3****d 1
Zikang Xiong 7****g 1
kplers 9****s 1
kronion k****n 1
and 1 more...
Committer Domains (Top 20 + Academic)
ucsb.edu: 1 ernestus.de: 1 gleave.me: 1 ensta.org: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 123
  • Total pull requests: 107
  • Average time to close issues: 3 months
  • Average time to close pull requests: 13 days
  • Total issue authors: 98
  • Total pull request authors: 31
  • Average comments per issue: 3.4
  • Average comments per pull request: 1.68
  • Merged pull requests: 73
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 21
  • Pull requests: 37
  • Average time to close issues: 6 days
  • Average time to close pull requests: 1 day
  • Issue authors: 21
  • Pull request authors: 13
  • Average comments per issue: 0.76
  • Average comments per pull request: 0.32
  • Merged pull requests: 17
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • vahidqo (4)
  • ashleychung830 (3)
  • Pborz (3)
  • araffin (3)
  • gowthamnatarajan (3)
  • anilkurkcu (3)
  • koliber31 (2)
  • qgallouedec (2)
  • CAI23sbP (2)
  • EloyAnguiano (2)
  • tingtingLiuLiu (2)
  • drulye (2)
  • zbenmo (2)
  • AlexPasqua (2)
  • btabia (2)
Pull Request Authors
  • araffin (59)
  • qgallouedec (16)
  • AlexPasqua (5)
  • Soham4001A (4)
  • pseudo-rnd-thoughts (2)
  • DanielAvdar (2)
  • KiuIras (2)
  • Armandpl (2)
  • akbaig (2)
  • icheered (2)
  • kplers (2)
  • corentinlger (2)
  • gcroci2 (2)
  • akanto (2)
  • jak3122 (2)
Top Labels
Issue Labels
question (59) enhancement (29) more information needed (18) custom gym env (14) bug (11) duplicate (9) help wanted (6) documentation (6) RTFM (4) No tech support (3) check the checkboxes (2) check the checklist (2) trading warning (1)
Pull Request Labels

Packages

  • Total packages: 4
  • Total downloads:
    • pypi 80,616 last-month
  • Total docker downloads: 529
  • Total dependent packages: 17
    (may contain duplicates)
  • Total dependent repositories: 154
    (may contain duplicates)
  • Total versions: 112
  • Total maintainers: 6
pypi.org: sb3-contrib

Contrib package of Stable Baselines3, experimental code.

  • Versions: 73
  • Dependent Packages: 17
  • Dependent Repositories: 154
  • Downloads: 80,601 Last month
  • Docker Downloads: 529
Rankings
Dependent packages count: 0.7%
Dependent repos count: 1.2%
Downloads: 1.4%
Average: 2.4%
Docker downloads count: 3.3%
Stargazers count: 3.4%
Forks count: 4.1%
Maintainers (5)
araffin ernestum hill-a Miffyli AdamGleave
Last synced: 6 months ago
proxy.golang.org: github.com/stable-baselines-team/stable-baselines3-contrib
  • Versions: 19
  • Dependent Packages: 0
  • Dependent Repositories: 0
Rankings
Dependent packages count: 5.5%
Average: 5.7%
Dependent repos count: 5.9%
Last synced: 6 months ago
proxy.golang.org: github.com/Stable-Baselines-Team/stable-baselines3-contrib
  • Versions: 19
  • Dependent Packages: 0
  • Dependent Repositories: 0
Rankings
Dependent packages count: 5.5%
Average: 5.7%
Dependent repos count: 5.9%
Last synced: 6 months ago
pypi.org: vls-sb3-contrib

Contrib package of Stable Baselines3, experimental code.

  • Versions: 1
  • Dependent Packages: 0
  • Dependent Repositories: 0
  • Downloads: 15 Last month
Rankings
Dependent packages count: 9.1%
Average: 30.2%
Dependent repos count: 51.3%
Maintainers (1)
bassnorn
Last synced: 6 months ago

Dependencies

setup.py pypi
  • stable_baselines3 >=1.5.1a7
.github/workflows/ci.yml actions
  • actions/checkout v3 composite
  • actions/setup-python v4 composite