Timezone: »

PettingZoo: Gym for Multi-Agent Reinforcement Learning
J Terry · Benjamin Black · Nathaniel Grammel · Mario Jayakumar · Ananth Hari · Ryan Sullivan · Luis S Santos · Clemens Dieffendahl · Caroline Horsch · Rodrigo Perez-Vicente · Niall Williams · Yashas Lokesh · Praveen Ravi

Thu Dec 09 08:30 AM -- 10:00 AM (PST) @

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.

Author Information

J Terry (University of Maryland College Park (SSO))
Benjamin Black (University of Maryland)
Nathaniel Grammel (University of Maryland, College Park)
Mario Jayakumar
Ananth Hari
Ryan Sullivan (University of Maryland)
Luis S Santos (University of Maryland, College Park)
Clemens Dieffendahl (Technical University Berlin)
Caroline Horsch (University of Maryland)
Rodrigo Perez-Vicente (University of Maryland)
Niall Williams
Yashas Lokesh
Praveen Ravi

More from the Same Authors