Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents
This provides a scalable environment for studying multiagent AI, addressing the need for robust policies in competitive scenarios, though it is incremental as it builds on existing game-based simulation concepts.
The paper tackles the challenge of training intelligent agents in large-scale multiagent settings by introducing Neural MMO, a game environment inspired by MMORPGs, and finds that larger populations incentivize more skillful behaviors and niche specialization, with agents outperforming those from smaller populations.
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. We present an artificial intelligence research environment, inspired by the human game genre of MMORPGs (Massively Multiplayer Online Role-Playing Games, a.k.a. MMOs), that aims to simulate this setting in microcosm. As with MMORPGs and the real world alike, our environment is persistent and supports a large and variable number of agents. Our environment is well suited to the study of large-scale multiagent interaction: it requires that agents learn robust combat and navigation policies in the presence of large populations attempting to do the same. Baseline experiments reveal that population size magnifies and incentivizes the development of skillful behaviors and results in agents that outcompete agents trained in smaller populations. We further show that the policies of agents with unshared weights naturally diverge to fill different niches in order to avoid competition.