# PettingZoo: Gym for Multi-Agent Reinforcement Learning

Source: [PettingZoo: Gym for Multi-Agent Reinforcement Learning](<https://www.sota2.com/research/paper/68fa6b471e209131cea2d3d5>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:44:09.187Z

Authors: J. K. Terry, Benjamin Black, Nathaniel Grammel, Mario Jayakumar, Ananth Hari, Ryan Sullivan, Luis Santos, Rodrigo Perez, Caroline Horsch, Clemens Dieffendahl, Niall L. Williams, Yashas Lokesh, Praveen Ravi

Published: 2020-09-30T06:42:09.000Z

## 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 games commonly used in MARL and accordingly can promote confusing bugs that are hard to detect, and that the AEC games model addresses these problems.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Cyber Deception on Cyber Environment (C) simulated (train)](<https://www.sota2.com/research/sota/cyber-deception-on-cyber-environment-c-simulated-train.md>): Cyber Deception; Cyber Environment (C) simulated (train); Average Episode Length: 5.19.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2009.14471>)

[PDF](<https://arxiv.org/pdf/2009.14471.pdf>)
