PettingZoo: Gym for Multi-Agent Reinforcement Learning

J K Terry, Benjamin Black, Mario Jayakumar, Ananth Hari, Luis Santos, Clemens Dieffendahl, Niall L Williams, Yashas Lokesh, Ryan Sullivan, Caroline Horsch, Praveen Ravi

Keywords: Reinforcement Learning, Multi-agent Reinforcement Learning

Abstract: OpenAI's Gym library contains a large, diverse set of environments that are useful benchmarks in reinforcement learning, under a single elegant Python API (with tools to develop new compliant environments) . The introduction of this library has proven a watershed moment for the reinforcement learning community, because it created an accessible set of benchmark environments that everyone could use (including wrapper important existing libraries), and because a standardized API let RL learning methods and environments from anywhere be trivially exchanged. This paper similarly introduces PettingZoo, a library of diverse set of multi-agent environments under a single elegant Python API, with tools to easily make new compliant environments.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: We introduce a large library that's essentially Gym for multi-agent reinforcement learning

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2009.14471/code)

Reviewed Version (pdf): https://openreview.net/references/pdf?id=x_9O0dCn0u