The Neural MMO Platform for Massively Multiagent ResearchDownload PDF

Published: 29 Jul 2021, Last Modified: 22 Oct 2023NeurIPS 2021 Datasets and Benchmarks Track (Round 1)Readers: Everyone
Keywords: Environment, Multiagent, Reinforcement Learning, Simulation, MMO, Platform
TL;DR: Neural MMO is a computationally accessible research platform that combines large agent populations, long time horizons, open-ended tasks, and modular game systems.
Abstract: 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.
Supplementary Material: zip
URL: neuralmmo.github.io
Contribution Process Agreement: Yes
Dataset Url: neuralmmo.github.io
Dataset Embargo: N/A
License: MIT License
Author Statement: Yes
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/arxiv:2110.07594/code)
4 Replies

Loading