Hurts to Be Too Early: Benefits and Drawbacks of Communication in Multi-Agent Learning

Published

Conference Paper

© 2019 IEEE. We study a multi-agent partially observable environment in which autonomous agents aim to coordinate their actions, while also learning the parameters of the unknown environment through repeated interactions. In particular, we focus on the role of communication in a multi-agent reinforcement learning problem. We consider a learning algorithm in which agents make decisions based on their own observations of the environment, as well as the observations of other agents, which are collected through communication between agents. We first identify two potential benefits of this type of information sharing when agents' observation quality is heterogeneous: (1) it can facilitate coordination among agents, and (2) it can enhance the learning of all participants, including the better informed agents. We show however that these benefits of communication depend in general on its timing, so that delayed information sharing may be preferred in certain scenarios.

Full Text

Duke Authors

Cited Authors

  • Naghizadeh, P; Gorlatova, M; Lan, AS; Chiang, M

Published Date

  • April 1, 2019

Published In

Volume / Issue

  • 2019-April /

Start / End Page

  • 622 - 630

International Standard Serial Number (ISSN)

  • 0743-166X

International Standard Book Number 13 (ISBN-13)

  • 9781728105154

Digital Object Identifier (DOI)

  • 10.1109/INFOCOM.2019.8737652

Citation Source

  • Scopus