Neural MMO: A massively multiplayer game environment for intelligent agents

Joseph Suarez, Yilun Du, Phillip Isola, Igor Mordatch

Abstract: We present an artificial intelligence research platform inspired by the human game genre of MMORPGs (Massively Multiplayer Online Role-Playing Games, a.k.a. MMOs). We demonstrate how this platform can be used to study behavior and learning in large populations of neural agents. Unlike currently popular game environments, our platform supports persistent environments, with variable number of agents, and open-ended task descriptions. The emergence of complex life on Earth is often attributed to the arms race that ensued from a huge number of organisms all competing for finite resources. Our platform aims to simulate this setting in microcosm: we conduct a series of experiments to test how large-scale multiagent competition can incentivize the development of skillful behavior. We find that population size magnifies the complexity of the behaviors that emerge and results in agents that out-compete agents trained in smaller populations.

Keywords: MMO, Multiagent, Game, Reinforcement Learning, Platform, Framework, Niche Formation, Exploration

TL;DR: An MMO-inspired research game platform for studying emergent behaviors of large populations in a complex environment