VAIN: Attentional multi-agent predictive modeling

Yedid Hoshen*

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

132 Scopus citations

Abstract

Multi-agent predictive modeling is an essential step for understanding physical, social and team-play systems. Recently, Interaction Networks (INs) were proposed for the task of modeling multi-agent physical systems. One of the drawbacks of INs is scaling with the number of interactions in the system (typically quadratic or higher order in the number of agents). In this paper we introduce VAIN, a novel attentional architecture for multi-agent predictive modeling that scales linearly with the number of agents. We show that VAIN is effective for multiagent predictive modeling. Our method is evaluated on tasks from challenging multi-agent prediction domains: chess and soccer, and outperforms competing multi-agent approaches.

Original languageAmerican English
Pages (from-to)2702-2712
Number of pages11
JournalAdvances in Neural Information Processing Systems
Volume2017-December
StatePublished - 2017
Externally publishedYes
Event31st Annual Conference on Neural Information Processing Systems, NIPS 2017 - Long Beach, United States
Duration: 4 Dec 20179 Dec 2017

Bibliographical note

Publisher Copyright:
© 2017 Neural information processing systems foundation. All rights reserved.

Fingerprint

Dive into the research topics of 'VAIN: Attentional multi-agent predictive modeling'. Together they form a unique fingerprint.

Cite this