Skip to content

Commit 6554907

Browse files
Update citation to Gymnasium Arxiv paper (#1135)
1 parent 4a85589 commit 6554907

File tree

3 files changed

+45
-39
lines changed

3 files changed

+45
-39
lines changed

Diff for: CITATION.cff

+32-21
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,10 @@
1+
# This CITATION.cff file was generated with cffinit.
2+
# Visit https://bit.ly/cffinit to generate yours today!
3+
14
cff-version: 1.2.0
2-
title: Gymnasium
5+
title: >-
6+
Gymnasium: A Standard Interface for Reinforcement Learning
7+
Environments
38
message: >-
49
If you use this software, please cite it using the
510
metadata from this file.
@@ -8,22 +13,22 @@ authors:
813
- given-names: Mark
914
family-names: Towers
1015
11-
affiliation: University of Southampton
16+
affiliation: University of Southampton & Farama Foundation
1217
orcid: 'https://orcid.org/0000-0002-2609-2041'
13-
- given-names: Jordan K
14-
family-names: Terry
15-
16-
affiliation: Farama Foundation
17-
orcid: 'https://orcid.org/0009-0006-4511-3756'
1818
- given-names: Ariel
1919
family-names: Kwiatkowski
2020
2121
affiliation: Farama Foundation
2222
orcid: 'https://orcid.org/0000-0002-9391-9993'
23+
- given-names: Jordan K
24+
family-names: Terry
25+
26+
affiliation: Farama Foundation
27+
orcid: 'https://orcid.org/0009-0006-4511-3756'
2328
- given-names: John U.
2429
family-names: Balis
2530
26-
affiliation: University of Wisconsin - Madison
31+
affiliation: Independent Researcher
2732
- given-names: Gianluca
2833
name-particle: de
2934
family-names: Cola
@@ -36,22 +41,22 @@ authors:
3641
- given-names: Manuel
3742
family-names: Goulão
3843
39-
affiliation: Instituto Superior Tecnico
44+
affiliation: NeuralShift
4045
orcid: 'https://orcid.org/0000-0001-6478-2038'
4146
- given-names: Andreas
4247
family-names: Kallinteris
4348
4449
affiliation: Technical University of Crete (TUC)
4550
orcid: 'https://orcid.org/0000-0002-6223-2670'
46-
- given-names: Arjun
47-
48-
family-names: KG
49-
affiliation: connectome.design
5051
- given-names: Markus
5152
family-names: Krimmel
5253
53-
affiliation: ETH
54+
affiliation: Independent Researcher
5455
orcid: 'https://orcid.org/0009-0005-0159-1214'
56+
- given-names: Arjun
57+
58+
family-names: KG
59+
affiliation: EarthBrain
5560
- given-names: Rodrigo
5661
family-names: Perez-Vicente
5762
@@ -70,25 +75,31 @@ authors:
7075
family-names: Tai
7176
7277
affiliation: Coventry University
73-
- given-names: Andrew Jin Shen
78+
- given-names: Hannah Jin Shen
7479
family-names: Tan
7580
7681
orcid: 'https://orcid.org/0009-0009-8772-5525'
82+
affiliation: Independent Researcher
7783
- given-names: Omar G.
7884
family-names: Younis
7985
8086
affiliation: University of Bologna
8187
orcid: 'https://orcid.org/0009-0004-2783-7932'
8288
identifiers:
83-
- type: doi
84-
value: 10.5281/zenodo.8127025
85-
description: Zenodo DOI
89+
- type: url
90+
value: 'https://arxiv.org/abs/2407.17032'
8691
repository-code: 'https://github.com/Farama-Foundation/Gymnasium'
8792
url: 'https://gymnasium.farama.org/'
8893
abstract: >-
89-
An API standard for single-agent reinforcement learning
90-
environments, with popular reference environments and
91-
related utilities (formerly Gym)
94+
Gymnasium is an open-source library providing an API for
95+
reinforcement learning environments. Its main contribution
96+
is a central abstraction for wide interoperability between
97+
benchmark environments and training algorithms. Gymnasium
98+
comes with various built-in environments and utilities to
99+
simplify researchers’ work along with being supported by
100+
most training libraries. This paper outlines the main
101+
design decisions for Gymnasium, its key features, and the
102+
differences to alternative APIs.
92103
keywords:
93104
- reinforcement learning
94105
- machine learning

Diff for: README.md

+12-17
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
[![Python](https://img.shields.io/pypi/pyversions/gymnasium.svg)](https://badge.fury.io/py/gymnasium)
22
[![PyPI](https://badge.fury.io/py/gymnasium.svg)](https://badge.fury.io/py/gymnasium)
3-
[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.8127025.svg)](https://doi.org/10.5281/zenodo.8127025)
3+
[![arXiv](https://img.shields.io/badge/arXiv-2407.17032-b31b1b.svg)](https://arxiv.org/abs/2407.17032)
44
[![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://pre-commit.com/)
55
[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
66

@@ -50,18 +50,15 @@ env.close()
5050

5151
## Notable Related Libraries
5252

53-
Please note that this is an incomplete list, and just includes libraries that the maintainers most commonly point newcommers to when asked for recommendations.
53+
Please note that this is an incomplete list, and just includes libraries that the maintainers most commonly point newcomers to when asked for recommendations.
5454

5555
* [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.
5656
* [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.
5757
* 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.
58-
* [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!
59-
60-
6158

6259
## Environment Versioning
6360

64-
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.
61+
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.
6562

6663
## Development Roadmap
6764

@@ -73,18 +70,16 @@ If you are financially able to do so and would like to support the development o
7370

7471
## Citation
7572

76-
You can cite Gymnasium as:
73+
You can cite Gymnasium using our related paper (https://arxiv.org/abs/2407.17032) as:
7774

7875
```
79-
@misc{towers_gymnasium_2023,
80-
title = {Gymnasium},
81-
url = {https://zenodo.org/record/8127025},
82-
abstract = {An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)},
83-
urldate = {2023-07-08},
84-
publisher = {Zenodo},
85-
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.},
86-
month = mar,
87-
year = {2023},
88-
doi = {10.5281/zenodo.8127026},
76+
@misc{towers2024gymnasium,
77+
title={Gymnasium: A Standard Interface for Reinforcement Learning Environments},
78+
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},
79+
year={2024},
80+
eprint={2407.17032},
81+
archivePrefix={arXiv},
82+
primaryClass={cs.LG},
83+
url={https://arxiv.org/abs/2407.17032},
8984
}
9085
```

Diff for: docs/index.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -87,14 +87,14 @@ environments/third_party_environments
8787
8888
tutorials/**/index
8989
tutorials/third-party-tutorials
90-
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>
9190
```
9291

9392
```{toctree}
9493
:hidden:
9594
:caption: Development
9695
9796
Github <https://github.com/Farama-Foundation/Gymnasium>
97+
Paper <https://arxiv.org/abs/2407.17032>
9898
gymnasium_release_notes/index
9999
gym_release_notes/index
100100
Contribute to the Docs <https://github.com/Farama-Foundation/Gymnasium/blob/main/docs/README.md>

0 commit comments

Comments
 (0)