The NeurIPS 2022 Neural MMO Challenge: A Massively Multiagent Competition with Specialization and Trade

Enhong Liu; Joseph Suarez; Chenhui You; Bo Wu; Bingcheng Chen; Jun Hu; Jiaxin Chen; Xiaolong Zhu; Clare Zhu; Julian Togelius; Sharada Mohanty; Weijun Hong; Rui Du; Yibing Zhang; Qinwen Wang; Xinhang Li; Zheng Yuan; Xiang Li; Yuejia Huang; Kun Zhang; Hanhui Yang; Shiqi Tang; Phillip Isola

The NeurIPS 2022 Neural MMO Challenge: A Massively Multiagent Competition with Specialization and Trade

Enhong Liu, Joseph Suarez, Chenhui You, Bo Wu, Bingcheng Chen, Jun Hu, Jiaxin Chen, Xiaolong Zhu, Clare Zhu, Julian Togelius, Sharada Mohanty, Weijun Hong, Rui Du, Yibing Zhang, Qinwen Wang, Xinhang Li, Zheng Yuan, Xiang Li, Yuejia Huang, Kun ZhangHanhui Yang, Shiqi Tang, Phillip Isola

Research output: Contribution to journal › Conference article › peer-review

Abstract

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-sourced¹ our baselines, including environment wrappers, benchmarks, and visualization tools for future research.

Original language	English (US)
Pages (from-to)	18-34
Number of pages	17
Journal	Proceedings of Machine Learning Research
Volume	220
State	Published - 2023
Event	36th Annual Conference on Neural Information Processing Systems - Competition Track, NeurIPS 2022 - Virtual, Online, United States Duration: Nov 28 2022 → Dec 9 2022

ASJC Scopus subject areas

Artificial Intelligence
Software
Control and Systems Engineering
Statistics and Probability

Cite this

Liu, E, Suarez, J, You, C, Wu, B, Chen, B, Hu, J, Chen, J, Zhu, X, Zhu, C, Togelius, J, Mohanty, S, Hong, W, Du, R, Zhang, Y, Wang, Q, Li, X, Yuan, Z, Li, X, Huang, Y, Zhang, K, Yang, H, Tang, S & Isola, P 2023, 'The NeurIPS 2022 Neural MMO Challenge: A Massively Multiagent Competition with Specialization and Trade', Proceedings of Machine Learning Research, vol. 220, pp. 18-34.

@article{2ec013882e1946d8a89ba81e276547f9,

title = "The NeurIPS 2022 Neural MMO Challenge: A Massively Multiagent Competition with Specialization and Trade",

abstract = "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{\textquoteright}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-sourced1 our baselines, including environment wrappers, benchmarks, and visualization tools for future research.",

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",

note = "Publisher Copyright: {\textcopyright} 2023 E. Liu et al.; 36th Annual Conference on Neural Information Processing Systems - Competition Track, NeurIPS 2022 ; Conference date: 28-11-2022 Through 09-12-2022",

year = "2023",

language = "English (US)",

volume = "220",

pages = "18--34",

journal = "Proceedings of Machine Learning Research",

issn = "2640-3498",

publisher = "ML Research Press",

}

TY - JOUR

T1 - The NeurIPS 2022 Neural MMO Challenge

T2 - 36th Annual Conference on Neural Information Processing Systems - Competition Track, NeurIPS 2022

AU - Liu, Enhong

AU - Suarez, Joseph

AU - You, Chenhui

AU - Wu, Bo

AU - Chen, Bingcheng

AU - Hu, Jun

AU - Chen, Jiaxin

AU - Zhu, Xiaolong

AU - Zhu, Clare

AU - Togelius, Julian

AU - Mohanty, Sharada

AU - Hong, Weijun

AU - Du, Rui

AU - Zhang, Yibing

AU - Wang, Qinwen

AU - Li, Xinhang

AU - Yuan, Zheng

AU - Li, Xiang

AU - Huang, Yuejia

AU - Zhang, Kun

AU - Yang, Hanhui

AU - Tang, Shiqi

AU - Isola, Phillip

PY - 2023

Y1 - 2023

N2 - 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-sourced1 our baselines, including environment wrappers, benchmarks, and visualization tools for future research.

AB - 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-sourced1 our baselines, including environment wrappers, benchmarks, and visualization tools for future research.

UR - http://www.scopus.com/inward/record.url?scp=85179138583&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85179138583&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85179138583

SN - 2640-3498

VL - 220

SP - 18

EP - 34

JO - Proceedings of Machine Learning Research

JF - Proceedings of Machine Learning Research

Y2 - 28 November 2022 through 9 December 2022

ER -

The NeurIPS 2022 Neural MMO Challenge: A Massively Multiagent Competition with Specialization and Trade

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this