The Neural MMO Platform for Massively Multiagent Research
This provides a new tool for researchers in multiagent AI to study complex, open-ended problems, though it is incremental as it builds on existing environment concepts.
The authors introduced Neural MMO, a platform for massively multiagent research that combines large populations, long horizons, open-ended tasks, and modular systems, where initial baselines show agents trained in large populations explore more and learn a progression of skills.
Neural MMO is a computationally accessible research platform that combines large agent populations, long time horizons, open-ended tasks, and modular game systems. Existing environments feature subsets of these properties, but Neural MMO is the first to combine them all. We present Neural MMO as free and open source software with active support, ongoing development, documentation, and additional training, logging, and visualization tools to help users adapt to this new setting. Initial baselines on the platform demonstrate that agents trained in large populations explore more and learn a progression of skills. We raise other more difficult problems such as many-team cooperation as open research questions which Neural MMO is well-suited to answer. Finally, we discuss current limitations of the platform, potential mitigations, and plans for continued development.