In this paper, we present the results of the NeurIPS-2022 Neural MMO Challenge, which attracted 500 participants and received over 1,600 submissions. Like the previous IJCAI-2022 Neural MMO Challenge, it involved agents from 16 populations surviving in procedurally generated worlds by collecting resources and defeating opponents. This year's competition runs on the latest v1.6 Neural MMO, which introduces new equipment, combat, trading, and a better scoring system. These elements combine to pose additional robustness and generalization challenges not present in previous competitions. This paper summarizes the design and results of the challenge, explores the potential of this environment as a benchmark for learning methods, and presents some practical reinforcement learning training approaches for complex tasks with sparse rewards. Additionally, we have open-sourced our baselines, including environment wrappers, benchmarks, and visualization tools for future research.
@article{arxiv.2311.03707,
title = {The NeurIPS 2022 Neural MMO Challenge: A Massively Multiagent Competition with Specialization and Trade},
author = {Enhong Liu and Joseph Suarez and Chenhui You and Bo Wu and Bingcheng Chen and Jun Hu and Jiaxin Chen and Xiaolong Zhu and Clare Zhu and Julian Togelius and Sharada Mohanty and Weijun Hong and Rui Du and Yibing Zhang and Qinwen Wang and Xinhang Li and Zheng Yuan and Xiang Li and Yuejia Huang and Kun Zhang and Hanhui Yang and Shiqi Tang and Phillip Isola},
journal= {arXiv preprint arXiv:2311.03707},
year = {2023}
}