Skip to yearly menu bar Skip to main content


Competition

The NeurIPS 2023 Neural MMO Challenge: Multi-Task Reinforcement Learning and Curriculum Generation

Joseph Suarez · Phillip Isola · David Bloomin · Kyoung Whan Choe · Hao Li · Ryan Sullivan · Nishaanth Kanna · Daniel Scott · Rose Shuman · Herbie Bradley · Louis Castricato · Chenghui Yu · Yuhao Jiang · Qimai Li · Jiaxin Chen · Xiaolong Zhu · Dipam Chakrabroty · Sharada Mohanty · Nikhil Pinnaparaju

Room 354

Abstract:

In this competition, participants train agents to complete a variety of tasks in Neural MMO 2.0 including foraging, combat, tool acquisition and usage, and item trading. Neural MMO is a simulated environment featuring 128 players, procedurally generated maps, and emergent complexity from interactions among agents. The competition features three tracks: two compute-limited academic tracks focused on multi-agent reinforcement learning and curriculum generation and one unrestricted track. This is the fourth challenge on Neural MMO, and the previous competitions have all yielded state-of-the-art performance on earlier versions of this environment as well as more general improvements to learning methods. The NeurIPS workshop will include presentations by the developers and by researchers in reinforcement learning and open-endedness.

Chat is not available.
Schedule