PettingZoo: Gym for Multi-Agent Reinforcement Learning

This paper introduces PettingZoo, a library of diverse sets of multi-agent environments under a single elegant Python API. PettingZoo was developed with the goal of accelerating research in multi-agent reinforcement learning, by creating a set of benchmark environments that are easily accessible to all researchers and a standardized API for the field, akin to what OpenAI's Gym library did for single-agent reinforcement learning. PettingZoo's API is unique from other multi-agent environment libraries in that it's API is able to sensibly represent all forms of environments encountered on multi-agent reinforcement learning. In addition to this, PettingZoo's API is very similar to Gym's and can be immediately understood by novices, while still providing access to all low-level features that may be needed for novel research.