Update citation to Gymnasium Arxiv paper (#1135)

This commit is contained in:
Mark Towers
2024-08-08 11:57:26 +01:00
committed by GitHub
parent 4a85589b92
commit 6554907b08
3 changed files with 45 additions and 39 deletions

View File

@@ -1,5 +1,10 @@
# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!
cff-version: 1.2.0 cff-version: 1.2.0
title: Gymnasium title: >-
Gymnasium: A Standard Interface for Reinforcement Learning
Environments
message: >- message: >-
If you use this software, please cite it using the If you use this software, please cite it using the
metadata from this file. metadata from this file.
@@ -8,22 +13,22 @@ authors:
- given-names: Mark - given-names: Mark
family-names: Towers family-names: Towers
email: mt5g17@soton.ac.uk email: mt5g17@soton.ac.uk
affiliation: University of Southampton affiliation: University of Southampton & Farama Foundation
orcid: 'https://orcid.org/0000-0002-2609-2041' orcid: 'https://orcid.org/0000-0002-2609-2041'
- given-names: Jordan K
family-names: Terry
email: jkterry@farama.org
affiliation: Farama Foundation
orcid: 'https://orcid.org/0009-0006-4511-3756'
- given-names: Ariel - given-names: Ariel
family-names: Kwiatkowski family-names: Kwiatkowski
email: akwiatkowski@farama.org email: akwiatkowski@farama.org
affiliation: Farama Foundation affiliation: Farama Foundation
orcid: 'https://orcid.org/0000-0002-9391-9993' orcid: 'https://orcid.org/0000-0002-9391-9993'
- given-names: Jordan K
family-names: Terry
email: jkterry@farama.org
affiliation: Farama Foundation
orcid: 'https://orcid.org/0009-0006-4511-3756'
- given-names: John U. - given-names: John U.
family-names: Balis family-names: Balis
email: balis@wisc.edu email: balis@wisc.edu
affiliation: University of Wisconsin - Madison affiliation: Independent Researcher
- given-names: Gianluca - given-names: Gianluca
name-particle: de name-particle: de
family-names: Cola family-names: Cola
@@ -36,22 +41,22 @@ authors:
- given-names: Manuel - given-names: Manuel
family-names: Goulão family-names: Goulão
email: manuel.silva.goulao@tecnico.ulisboa.pt email: manuel.silva.goulao@tecnico.ulisboa.pt
affiliation: Instituto Superior Tecnico affiliation: NeuralShift
orcid: 'https://orcid.org/0000-0001-6478-2038' orcid: 'https://orcid.org/0000-0001-6478-2038'
- given-names: Andreas - given-names: Andreas
family-names: Kallinteris family-names: Kallinteris
email: akallinteris@tuc.gr email: akallinteris@tuc.gr
affiliation: Technical University of Crete (TUC) affiliation: Technical University of Crete (TUC)
orcid: 'https://orcid.org/0000-0002-6223-2670' orcid: 'https://orcid.org/0000-0002-6223-2670'
- given-names: Arjun
email: kg.arjun@gmail.com
family-names: KG
affiliation: connectome.design
- given-names: Markus - given-names: Markus
family-names: Krimmel family-names: Krimmel
email: markus.krimmel@student.uni-tuebingen.de email: markus.krimmel@student.uni-tuebingen.de
affiliation: ETH affiliation: Independent Researcher
orcid: 'https://orcid.org/0009-0005-0159-1214' orcid: 'https://orcid.org/0009-0005-0159-1214'
- given-names: Arjun
email: kg.arjun@gmail.com
family-names: KG
affiliation: EarthBrain
- given-names: Rodrigo - given-names: Rodrigo
family-names: Perez-Vicente family-names: Perez-Vicente
email: rperezvicente@farama.org email: rperezvicente@farama.org
@@ -70,25 +75,31 @@ authors:
family-names: Tai family-names: Tai
email: taijunjet@hotmail.com email: taijunjet@hotmail.com
affiliation: Coventry University affiliation: Coventry University
- given-names: Andrew Jin Shen - given-names: Hannah Jin Shen
family-names: Tan family-names: Tan
email: andrew.jinshen@gmail.com email: andrew.jinshen@gmail.com
orcid: 'https://orcid.org/0009-0009-8772-5525' orcid: 'https://orcid.org/0009-0009-8772-5525'
affiliation: Independent Researcher
- given-names: Omar G. - given-names: Omar G.
family-names: Younis family-names: Younis
email: omar.younis98@gmail.com email: omar.younis98@gmail.com
affiliation: University of Bologna affiliation: University of Bologna
orcid: 'https://orcid.org/0009-0004-2783-7932' orcid: 'https://orcid.org/0009-0004-2783-7932'
identifiers: identifiers:
- type: doi - type: url
value: 10.5281/zenodo.8127025 value: 'https://arxiv.org/abs/2407.17032'
description: Zenodo DOI
repository-code: 'https://github.com/Farama-Foundation/Gymnasium' repository-code: 'https://github.com/Farama-Foundation/Gymnasium'
url: 'https://gymnasium.farama.org/' url: 'https://gymnasium.farama.org/'
abstract: >- abstract: >-
An API standard for single-agent reinforcement learning Gymnasium is an open-source library providing an API for
environments, with popular reference environments and reinforcement learning environments. Its main contribution
related utilities (formerly Gym) is a central abstraction for wide interoperability between
benchmark environments and training algorithms. Gymnasium
comes with various built-in environments and utilities to
simplify researchers work along with being supported by
most training libraries. This paper outlines the main
design decisions for Gymnasium, its key features, and the
differences to alternative APIs.
keywords: keywords:
- reinforcement learning - reinforcement learning
- machine learning - machine learning

View File

@@ -1,6 +1,6 @@
[![Python](https://img.shields.io/pypi/pyversions/gymnasium.svg)](https://badge.fury.io/py/gymnasium) [![Python](https://img.shields.io/pypi/pyversions/gymnasium.svg)](https://badge.fury.io/py/gymnasium)
[![PyPI](https://badge.fury.io/py/gymnasium.svg)](https://badge.fury.io/py/gymnasium) [![PyPI](https://badge.fury.io/py/gymnasium.svg)](https://badge.fury.io/py/gymnasium)
[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.8127025.svg)](https://doi.org/10.5281/zenodo.8127025) [![arXiv](https://img.shields.io/badge/arXiv-2407.17032-b31b1b.svg)](https://arxiv.org/abs/2407.17032)
[![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://pre-commit.com/) [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://pre-commit.com/)
[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black) [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
@@ -50,18 +50,15 @@ env.close()
## Notable Related Libraries ## Notable Related Libraries
Please note that this is an incomplete list, and just includes libraries that the maintainers most commonly point newcommers to when asked for recommendations. Please note that this is an incomplete list, and just includes libraries that the maintainers most commonly point newcomers to when asked for recommendations.
* [CleanRL](https://github.com/vwxyzjn/cleanrl) is a learning library based on the Gymnasium API. It is designed to cater to newer people in the field and provides very good reference implementations. * [CleanRL](https://github.com/vwxyzjn/cleanrl) is a learning library based on the Gymnasium API. It is designed to cater to newer people in the field and provides very good reference implementations.
* [PettingZoo](https://github.com/Farama-Foundation/PettingZoo) is a multi-agent version of Gymnasium with a number of implemented environments, i.e. multi-agent Atari environments. * [PettingZoo](https://github.com/Farama-Foundation/PettingZoo) is a multi-agent version of Gymnasium with a number of implemented environments, i.e. multi-agent Atari environments.
* The Farama Foundation also has a collection of many other [environments](https://farama.org/projects) that are maintained by the same team as Gymnasium and use the Gymnasium API. * The Farama Foundation also has a collection of many other [environments](https://farama.org/projects) that are maintained by the same team as Gymnasium and use the Gymnasium API.
* [Comet](https://www.comet.com/site/?utm_source=gymnasium&utm_medium=partner&utm_campaign=partner_gymnasium_2023&utm_content=github) is a free ML-Ops tool that tracks rewards, metrics, hyperparameters, and code for ML training runs. Comet has an easy-to use integration with Gymnasium, here's a [tutorial](https://bit.ly/CometGymnasiumIntegration) on how to use them together! Comet is a sponsor of the Farama Foundation!
## Environment Versioning ## Environment Versioning
Gymnasium keeps strict versioning for reproducibility reasons. All environments end in a suffix like "-v0". When changes are made to environments that might impact learning results, the number is increased by one to prevent potential confusion. These inherit from Gym. Gymnasium keeps strict versioning for reproducibility reasons. All environments end in a suffix like "-v0". When changes are made to environments that might impact learning results, the number is increased by one to prevent potential confusion. These were inherited from Gym.
## Development Roadmap ## Development Roadmap
@@ -73,18 +70,16 @@ If you are financially able to do so and would like to support the development o
## Citation ## Citation
You can cite Gymnasium as: You can cite Gymnasium using our related paper (https://arxiv.org/abs/2407.17032) as:
``` ```
@misc{towers_gymnasium_2023, @misc{towers2024gymnasium,
title = {Gymnasium}, title={Gymnasium: A Standard Interface for Reinforcement Learning Environments},
url = {https://zenodo.org/record/8127025}, author={Mark Towers and Ariel Kwiatkowski and Jordan Terry and John U. Balis and Gianluca De Cola and Tristan Deleu and Manuel Goulão and Andreas Kallinteris and Markus Krimmel and Arjun KG and Rodrigo Perez-Vicente and Andrea Pierré and Sander Schulhoff and Jun Jet Tai and Hannah Tan and Omar G. Younis},
abstract = {An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)}, year={2024},
urldate = {2023-07-08}, eprint={2407.17032},
publisher = {Zenodo}, archivePrefix={arXiv},
author = {Towers, Mark and Terry, Jordan K. and Kwiatkowski, Ariel and Balis, John U. and Cola, Gianluca de and Deleu, Tristan and Goulão, Manuel and Kallinteris, Andreas and KG, Arjun and Krimmel, Markus and Perez-Vicente, Rodrigo and Pierré, Andrea and Schulhoff, Sander and Tai, Jun Jet and Shen, Andrew Tan Jin and Younis, Omar G.}, primaryClass={cs.LG},
month = mar, url={https://arxiv.org/abs/2407.17032},
year = {2023},
doi = {10.5281/zenodo.8127026},
} }
``` ```

View File

@@ -87,7 +87,6 @@ environments/third_party_environments
tutorials/**/index tutorials/**/index
tutorials/third-party-tutorials tutorials/third-party-tutorials
Comet Tutorial <https://www.comet.com/docs/v2/integrations/ml-frameworks/gymnasium/?utm_source=gymnasium&utm_medium=partner&utm_campaign=partner_gymnasium_2023&utm_content=docs_gymnasium>
``` ```
```{toctree} ```{toctree}
@@ -95,6 +94,7 @@ Comet Tutorial <https://www.comet.com/docs/v2/integrations/ml-frameworks/gymnasi
:caption: Development :caption: Development
Github <https://github.com/Farama-Foundation/Gymnasium> Github <https://github.com/Farama-Foundation/Gymnasium>
Paper <https://arxiv.org/abs/2407.17032>
gymnasium_release_notes/index gymnasium_release_notes/index
gym_release_notes/index gym_release_notes/index
Contribute to the Docs <https://github.com/Farama-Foundation/Gymnasium/blob/main/docs/README.md> Contribute to the Docs <https://github.com/Farama-Foundation/Gymnasium/blob/main/docs/README.md>