Peter Stone's Selected Publications

Classified by TopicClassified by Publication TypeSorted by DateSorted by First Author Last NameClassified by Funding Source


A Penny for Your Thoughts: The Value of Communication in Ad Hoc Teamwork

A Penny for Your Thoughts: The Value of Communication in Ad Hoc Teamwork.
Reuth Mirsky, William Macke, Andy Wang, Harel Yedidsion, and Peter Stone.
In Proceedings of the 29th International Joint Conference on Artificial Intelligence, July 2020.
15-minute presentation

Download

[PDF]1.2MB  [slides.pdf]1.4MB  

Abstract

In ad hoc teamwork, multiple agents need to collaborate without having knowledge about their teammates or their plans a priori. A common assumption in this research area is that the agents cannot communicate. However, just as two random people may speak the same language, autonomous teammates may also happen to share a communication protocol. This paper considers how such a shared protocol can be leveraged, introducing a means to reason about Communication in Ad Hoc Teamwork (CAT). The goal of this work is enabling improved ad hoc teamwork by judiciously leveraging the ability of the team to communicate.We situate our study within a novel CAT scenario, involving tasks with multiple steps, where teammates' plans are unveiled over time. In this context, the paper proposes methods to reason about the timing and value of communication and introduces an algorithm for an ad hoc agent to leverage these methods. Finally, we introduces a new multiagent domain, the tool fetching domain, and we studyhow varying this domain's properties affects the usefulness of communication. Empirical results show the benefits of explicit reasoning about communication content and timing in ad hoc teamwork.

BibTeX Entry

@inproceedings{IJCAI2020-Mirsky,
	author="Reuth Mirsky and William Macke and Andy Wang and Harel Yedidsion and Peter Stone",
	title="A Penny for Your Thoughts: The Value of Communication in Ad Hoc Teamwork",
	booktitle="Proceedings of the 29th International Joint Conference on Artificial Intelligence",
	location="Yokohama, Japan",
	abstract="In ad hoc teamwork, multiple agents need to collaborate without having knowledge 
		about their teammates or their plans a priori. A common assumption in this research 
		area is that the agents cannot communicate. However, just as two random people may 
		speak the same language, autonomous teammates may also happen to share a 
		communication protocol. This paper considers how such a shared protocol can be 
		leveraged, introducing a means to reason about Communication in Ad Hoc Teamwork 
		(CAT). The goal of this work is enabling improved ad hoc teamwork by judiciously 
		leveraging the ability of the team to communicate.
We situate our study within a novel CAT scenario, involving tasks with multiple steps, where 
teammates' plans are unveiled over time. In this context, the paper proposes methods to reason about 
the timing and value of communication and introduces an algorithm for an ad hoc agent to leverage 
these methods. Finally, we introduces a new multiagent domain, the tool fetching domain, and we study
how varying this domain's properties affects the usefulness of communication. Empirical results show 
the benefits of explicit reasoning about communication content and timing in ad hoc teamwork.",
        wwwnote={<a href="https://videos.ijcai20.org/26703/index.html">15-minute presentation</a>},
	month="July",
	year=2020}

Generated by bib2html.pl (written by Patrick Riley ) on Mon Mar 25, 2024 00:05:13