PettingZoo: Gym for Multi-Agent Reinforcement Learning
J K Terry, Benjamin J Black, Nathaniel Grammel, Mario Jayakumar, Ananth Hari, Ryan Sullivan, Luis Santos, Clemens Dieffendahl
Abstract
This paper introduces the PettingZoo library and the accompanying Agent Environment Cycle (``"AEC") games model. PettingZoo is a library of diverse sets of multi-agent environments with a universal, elegant Python API. PettingZoo was developed with the goal of accelerating research in Multi-Agent Reinforcement Learning (``"MARL"), by making work more interchangeable, accessible and reproducible akin to what OpenAI's Gym library did for single-agent reinforcement learning. PettingZoo's API, while inheriting many features of Gym, is unique amongst MARL APIs in that it's based around the novel AEC games model. We argue, in part through case studies on major problems in popular MARL environments, that the popular game models are poor conceptual models of the games commonly used with MARL, that they promote severe bugs that are hard to detect, and that the AEC games model addresses these problems.
BibTeX
@inproceedings{
terry2021pettingzoo,
title={PettingZoo: Gym for Multi-Agent Reinforcement Learning},
author={J K Terry and Benjamin J Black and Nathaniel Grammel and Mario Jayakumar and Ananth Hari and Ryan Sullivan and Luis Santos and Clemens Dieffendahl and Caroline Horsch and Rodrigo De Lazcano Perez-Vicente and Niall L Williams and Yashas Lokesh and Praveen Ravi},
booktitle={Advances in Neural Information Processing Systems},
editor={A. Beygelzimer and Y. Dauphin and P. Liang and J. Wortman Vaughan},
year={2021},
url={https://openreview.net/forum?id=fLnsj7fpbPI}
}