PettingZoo: Gym for Multi-Agent Reinforcement Learning
This work offers a tool for MARL researchers to improve interchangeability, accessibility, and reproducibility, similar to OpenAI Gym's impact on single-agent RL.
The paper introduces the PettingZoo library and the Agent Environment Cycle (AEC) games model to accelerate multi-agent reinforcement learning (MARL) research by providing a universal Python API, addressing issues like bugs and confusion in existing models.
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.