rlberry

An easy-to-use reinforcement learning library for research and education.

https://github.com/rlberry-py/rlberry

Science Score: 67.0%

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
    Found 1 DOI reference(s) in README
  • Academic publication links
  • Committers with academic emails
    3 of 25 committers (12.0%) from academic institutions
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (17.1%) to scientific vocabulary

Keywords

multi-armed-bandits reinforcement-learning reinforcement-learning-algorithms reinforcement-learning-environments

Keywords from Contributors

ode mesh hydrology graph-generation data-profilers geoscience datacleaner spacy-extension pipeline-testing pypi
Last synced: 6 months ago · JSON representation ·

Repository

An easy-to-use reinforcement learning library for research and education.

Basic Info
Statistics
  • Stars: 169
  • Watchers: 7
  • Forks: 30
  • Open Issues: 40
  • Releases: 12
Topics
multi-armed-bandits reinforcement-learning reinforcement-learning-algorithms reinforcement-learning-environments
Created over 5 years ago · Last pushed 7 months ago
Metadata Files
Readme Contributing License Code of conduct Citation

README.md

A Reinforcement Learning Library for Research and Education

Python Version contributors codecov


What is rlberry?

Writing reinforcement learning algorithms is fun! But after the fun, we have lots of boring things to implement: run our agents in parallel, average and plot results, optimize hyperparameters, compare to baselines, create tricky environments etc etc!

rlberry is a Python library that makes your life easier by doing all these things with a few lines of code, so that you can spend most of your time developing agents. rlberry also provides implementations of several RL agents, benchmark environments and many other useful tools.

We provide you a number of tools to help you achieve reproducibility, statistically comparisons of RL agents, and nice visualization.

Installation

Install the latest (minimal) version for a stable release.

bash pip install -U rlberry

The documentation includes more installation instructions.

Getting started

In our dev documentation, you will find quick starts to the library and a user guide with a few tutorials on using rlberry, and some examples. See also the stable documentation for the documentation corresponding to the last release.

Changelog

See the changelog for a history of the changes made to rlberry.

Other rlberry projects

rlberry-scool : It’s the repository used for teaching purposes. These are mainly basic agents and environments, in a version that makes it easier for students to learn.

rlberry-research : It’s the repository where our research team keeps some agents, environments, or tools compatible with rlberry. It’s a permanent “work in progress” repository, and some code may be not maintained anymore.

Citing rlberry

If you use rlberry in scientific publications, we would appreciate citations using the following Bibtex entry:

bibtex @misc{rlberry, author = {Domingues, Omar Darwiche and Flet-Berliac, Yannis and Leurent, Edouard and M{\'e}nard, Pierre and Shang, Xuedong and Valko, Michal}, doi = {10.5281/zenodo.5544540}, month = {10}, title = {{rlberry - A Reinforcement Learning Library for Research and Education}}, url = {https://github.com/rlberry-py/rlberry}, year = {2021} }

About us

This project was initiated and is actively maintained by INRIA SCOOL team. More information here.

Contributing

Want to contribute to rlberry? Please check our contribution guidelines. If you want to add any new agents or environments, do not hesitate to open an issue!

Owner

  • Name: rlberry-py
  • Login: rlberry-py
  • Kind: organization

Citation (CITATION.cff)

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "Domingues"
  given-names: "Omar Darwiche"
- family-names: "Flet-Berliac"
  given-names: "Yannis"
- family-names: "Leurent"
  given-names: "Edouard"
- family-names: "Ménard"
  given-names: "Pierre"
- family-names: "Shang"
  given-names: "Xuedong"
- family-names: "Valko"
  given-names: "Michal"

title: "rlberry - A Reinforcement Learning Library for Research and Education"
abbreviation: rlberry
version: 0.2.2-dev
doi: 10.5281/zenodo.5223307
date-released: 2021-10-01
url: "https://github.com/rlberry-py/rlberry"

GitHub Events

Total
  • Issues event: 2
  • Watch event: 8
  • Issue comment event: 42
  • Push event: 61
  • Pull request event: 8
  • Pull request review comment event: 12
  • Pull request review event: 11
Last Year
  • Issues event: 2
  • Watch event: 8
  • Issue comment event: 42
  • Push event: 61
  • Pull request event: 8
  • Pull request review comment event: 12
  • Pull request review event: 11

Committers

Last synced: about 1 year ago

All Time
  • Total Commits: 1,173
  • Total Committers: 25
  • Avg Commits per committer: 46.92
  • Development Distribution Score (DDS): 0.624
Past Year
  • Commits: 94
  • Committers: 4
  • Avg Commits per committer: 23.5
  • Development Distribution Score (DDS): 0.34
Top Committers
Name Email Commits
Omar D o****h@g****m 441
TimotheeMathieu t****u@i****r 235
xuedong s****g@y****r 146
Ju T 5****1 94
Edouard Leurent e****t@g****m 77
yfletberliac y****e@g****m 65
sauxpa p****x@g****m 27
Matheus M. Centa m****a@g****m 18
KohlerHECTOR K****R 16
sauxpa p****x@i****r 8
AleShi94 a****a@s****u 6
Pierre Ménard m****r@g****m 6
Riccardo Della Vecchia r****1@g****m 6
Hector Kohler h****r@u****n 6
Rémy Degenne r****e@g****m 4
Antoine Moulin a****n@t****r 4
pre-commit-ci[bot] 6****] 3
Waris Radji w****4@g****m 2
brahimdriss b****s 2
TimotheeMathieu t****u@u****r 2
dependabot[bot] 4****] 1
YannBerthelot 4****t 1
The Codacy Badger b****r@c****m 1
Boris Hamadej 9****j 1
AdrienneTuynman 1****n 1

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 53
  • Total pull requests: 126
  • Average time to close issues: 4 months
  • Average time to close pull requests: about 1 month
  • Total issue authors: 7
  • Total pull request authors: 17
  • Average comments per issue: 0.89
  • Average comments per pull request: 3.37
  • Merged pull requests: 87
  • Bot issues: 0
  • Bot pull requests: 18
Past Year
  • Issues: 1
  • Pull requests: 9
  • Average time to close issues: N/A
  • Average time to close pull requests: 9 days
  • Issue authors: 1
  • Pull request authors: 2
  • Average comments per issue: 0.0
  • Average comments per pull request: 5.67
  • Merged pull requests: 6
  • Bot issues: 0
  • Bot pull requests: 0
Top Authors
Issue Authors
  • TimotheeMathieu (29)
  • JulienT01 (9)
  • KohlerHECTOR (5)
  • mmcenta (2)
  • RemyDegenne (2)
  • YannBerthelot (2)
  • riiswa (2)
  • AleShi94 (1)
Pull Request Authors
  • JulienT01 (71)
  • TimotheeMathieu (56)
  • dependabot[bot] (14)
  • KohlerHECTOR (6)
  • pre-commit-ci[bot] (4)
  • RemyDegenne (3)
  • riiswa (3)
  • AdrienneTuynman (2)
  • akrouriad (1)
  • BorisHamadej (1)
  • riccardodv (1)
  • YannBerthelot (1)
  • brahimdriss (1)
  • omardrwch (1)
  • AmirAflak (1)
Top Labels
Issue Labels
Marathon (16) enhancement (12) good first issue (9) documentation (9) style (5) discussion (4) bug (4) dependencies (2) question (1) help wanted (1) agent (1)
Pull Request Labels
ready for review (117) dependencies (15) Marathon (9) documentation (8) enhancement (3) ready for CI (3) agent (1)

Packages

  • Total packages: 1
  • Total downloads:
    • pypi 187 last-month
  • Total dependent packages: 1
  • Total dependent repositories: 3
  • Total versions: 16
  • Total maintainers: 4
pypi.org: rlberry

An easy-to-use reinforcement learning library for research and education

  • Versions: 16
  • Dependent Packages: 1
  • Dependent Repositories: 3
  • Downloads: 187 Last month
Rankings
Dependent repos count: 9.0%
Dependent packages count: 10.1%
Average: 12.7%
Downloads: 19.1%
Maintainers (4)
Last synced: 7 months ago

Dependencies

docs/requirements.txt pypi
  • matplotlib *
  • myst-parser *
  • numpydoc *
  • sphinx-gallery *
poetry.lock pypi
  • absl-py 1.1.0
  • alembic 1.8.0
  • attrs 21.4.0
  • autopage 0.5.1
  • cachetools 5.2.0
  • certifi 2022.5.18.1
  • charset-normalizer 2.0.12
  • cliff 3.10.1
  • cloudpickle 2.1.0
  • cmaes 0.8.2
  • cmd2 2.4.1
  • colorama 0.4.4
  • colorlog 6.6.0
  • cycler 0.11.0
  • dill 0.3.5.1
  • docopt 0.6.2
  • ffmpeg-python 0.2.0
  • fonttools 4.33.3
  • future 0.18.2
  • google-auth 2.6.6
  • google-auth-oauthlib 0.4.6
  • greenlet 1.1.2
  • grpcio 1.46.3
  • gym 0.21.0
  • idna 3.3
  • importlib-metadata 4.11.4
  • kiwisolver 1.4.2
  • mako 1.2.0
  • markdown 3.3.7
  • markupsafe 2.1.1
  • matplotlib 3.5.2
  • numpy 1.22.4
  • oauthlib 3.2.0
  • optuna 2.10.0
  • packaging 21.3
  • pandas 1.4.2
  • pbr 5.9.0
  • pillow 9.1.1
  • prettytable 3.3.0
  • protobuf 3.20.1
  • pyasn1 0.4.8
  • pyasn1-modules 0.2.8
  • pygame 2.1.2
  • pyopengl 3.1.6
  • pyparsing 3.0.9
  • pyperclip 1.8.2
  • pyreadline3 3.4.1
  • python-dateutil 2.8.2
  • pytz 2022.1
  • pyvirtualdisplay 3.0
  • pyyaml 6.0
  • requests 2.27.1
  • requests-oauthlib 1.3.1
  • rsa 4.8
  • scipy 1.8.1
  • seaborn 0.11.2
  • setuptools-scm 6.4.2
  • six 1.16.0
  • sqlalchemy 1.4.37
  • stable-baselines3 1.5.0
  • stevedore 3.5.0
  • tensorboard 2.9.0
  • tensorboard-data-server 0.6.1
  • tensorboard-plugin-wit 1.8.1
  • tomli 2.0.1
  • torch 1.11.0
  • tqdm 4.64.0
  • typing-extensions 4.2.0
  • urllib3 1.26.9
  • wcwidth 0.2.5
  • werkzeug 2.1.2
  • zipp 3.8.0
requirements.txt pypi
  • PyOpenGL ==3.1.5
  • PyOpenGL_accelerate ==3.1.5
  • dill *
  • docopt *
  • ffmpeg-python *
  • gym *
  • matplotlib *
  • numba *
  • numpy >=1.17
  • optuna *
  • pandas *
  • protobuf ==3.20.1
  • pygame *
  • pyvirtualdisplay *
  • pyyaml *
  • scipy >=1.6
  • seaborn *
  • stable-baselines3 *
  • tensorboard *
  • torch >=1.6.0
setup.py pypi
  • dill *
  • docopt *
  • gym *
  • matplotlib *
  • numpy >=1.17
  • pandas *
  • pygame *
  • pyyaml *
  • scipy >=1.6
  • seaborn *
.github/workflows/dunamai.yml actions
  • EndBug/add-and-commit v8 composite
  • actions/checkout v2 composite
  • actions/setup-python v2 composite
  • mtkennerly/dunamai-action v1 composite