Neural MMO 2.0: A Massively Multi-task Addition to Massively Multi-agent Learning
Joseph Suarez, David Bloomin, Kyoung Whan Choe, Hao Xiang Li, Ryan Sullivan, Nishaanth Kanna Ravichandran, Daniel Scott, Rose S Shuman
Abstract
Neural MMO 2.0 is a massively multi-agent and multi-task environment for reinforcement learning research. This version features a novel task-system that broadens the range of training settings and poses a new challenge in generalization: evaluation on and against tasks, maps, and opponents never seen during training. Maps are procedurally generated with 128 agents in the standard setting and 1-1024 supported overall. Version 2.0 is a complete rewrite of its predecessor with three-fold improved performance, effectively addressing simulation bottlenecks in online training. Enhancements to compatibility enable training with standard reinforcement learning frameworks designed for much simpler environments. Neural MMO 2.0 is free and open-source with comprehensive documentation available at neuralmmo.github.io and an active community Discord. To spark initial research on this new platform, we are concurrently running a competition at NeurIPS 2023.
BibTeX
@inproceedings{
suarez2023neural,
title={Neural {MMO} 2.0: A Massively Multi-task Addition to Massively Multi-agent Learning},
author={Joseph Suarez and David Bloomin and Kyoung Whan Choe and Hao Xiang Li and Ryan Sullivan and Nishaanth Kanna Ravichandran and Daniel Scott and Rose S Shuman and Herbie Bradley and Louis Castricato and Phillip Isola and Kirsty You and Yuhao Jiang and Qimai Li and Jiaxin Chen and Xiaolong Zhu},
booktitle={Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
year={2023},
url={https://openreview.net/forum?id=DSYuRMJnaY}
}