Saved in:
Bibliographic Details
Main Authors: Suárez, Joseph, Choe, Kyoung Whan, Bloomin, David, Gao, Jianming, Li, Yunkun, Feng, Yao, Pola, Saidinesh, Zhang, Kun, Zhu, Yonghui, Pinnaparaju, Nikhil, Li, Hao Xiang, Kanna, Nishaanth, Scott, Daniel, Sullivan, Ryan, Shuman, Rose S., de Alcântara, Lucas, Bradley, Herbie, You, Kirsty, Wu, Bo, Jiang, Yuhao, Li, Qimai, Chen, Jiaxin, Castricato, Louis, Zhu, Xiaolong, Isola, Phillip
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.12524
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • We present the results of the NeurIPS 2023 Neural MMO Competition, which attracted over 200 participants and submissions. Participants trained goal-conditional policies that generalize to tasks, maps, and opponents never seen during training. The top solution achieved a score 4x higher than our baseline within 8 hours of training on a single 4090 GPU. We open-source everything relating to Neural MMO and the competition under the MIT license, including the policy weights and training code for our baseline and for the top submissions.