Article

Communicating with unknown teammates

Authors:

Samuel Barrett,

Peter StoneAuthors Info & Claims

ECAI'14: Proceedings of the Twenty-first European Conference on Artificial Intelligence

Pages 45 - 50

Published: 18 August 2014 Publication History

Abstract

Past research has investigated a number of methods for coordinating teams of agents, but with the growing number of sources of agents, it is likely that agents will encounter teammates that do not share their coordination methods. Therefore, it is desirable for agents to adapt to these teammates, forming an effective ad hoc team. Past ad hoc teamwork research has focused on cases where the agents do not directly communicate. However when teammates do communicate, it can provide a valuable channel for coordination. Therefore, this paper tackles the problem of communication in ad hoc teams, introducing a minimal version of the multiagent, multi-armed bandit problem with limited communication between the agents. The theoretical results in this paper prove that this problem setting can be solved in polynomial time when the agent knows the set of possible teammates. Furthermore, the empirical results show that an agent can cooperate with a variety of teammates following unknown behaviors even when its models of these teammates are imperfect.

References

[1]

Peter Auer, Nicolò Cesa-Bianchi, and Paul Fischer, 'Finite-time analysis of the multiarmed bandit problem', Machine Learning, 47, 235-256, (May 2002).

[2]

Samuel Barrett and Peter Stone, 'An analysis framework for ad hoc teamwork tasks', in AAMAS '12, (June 2012).

[3]

Samuel Barrett, Peter Stone, Sarit Kraus, and Avi Rosenfeld, 'Teamwork with limited knowledge of teammates', in AAAI, (July 2013).

[4]

Michael Bowling and Peter McCracken, 'Coordination and adaptation in impromptu teams', in AAAI, (2005).

[5]

Prashant Doshi and Yifeng Zeng, 'Improved approximation of interactive dynamic influence diagrams using discriminative model updates', in AAMAS '09, (2009).

[6]

Piotr J. Gmytrasiewicz and Prashant Doshi, 'A framework for sequential planning in multi-agent settings', JAIR, 24(1), 49-79, (July 2005).

[7]

Claudia V. Goldman, Martin Allen, and Shlomo Zilberstein, 'Learning to communicate in a decentralized environment', Autonomous Agents and Multi-Agent Systems, 15(1), (2007).

[8]

B. Grosz and S. Kraus, 'The evolution of SharedPlans', in Foundations and Theories of Rational Agency, (1999).

[9]

Bryan Horling, Victor Lesser, Regis Vincent, Tom Wagner, Anita Raja, Shelley Zhang, Keith Decker, and Alan Garvey. The TAEMS White Paper, January 1999.

[10]

David Hsu, Wee Sun Lee, and Nan Rong, 'What makes some POMDP problems easy to approximate?', in NIPS, (2007).

[11]

Levente Kocsis and Csaba Szepesvari, 'Bandit based Monte-Carlo planning', in ECML '06, (2006).

[12]

Somchaya Liemhetcharat and Manuela Veloso, 'Modeling mutual capabilities in heterogeneous teams for role assignment', in IROS '11, pp. 3638-3644, (2011).

[13]

Martin L Puterman and Moon Chirl Shin, 'Modified policy iteration algorithms for discounted Markov decision problems', Management Science, 24(11), 1127-1137, (1978).

[14]

Avi Rosenfeld, Inon Zuckerman, Amos Azaria, and Sarit Kraus, 'Combining psychological models with machine learning to better predict people's decisions', Synthese, 189, 81-93, (2012).

[15]

David Silver and Joel Veness, 'Monte-Carlo planning in large POMDPs', in NIPS '10, (2010).

[16]

Peter Stone, Gal A. Kaminka, Sarit Kraus, and Jeffrey S. Rosenschein, 'Ad hoc autonomous agent teams: Collaboration without pre-coordination', in AAAI '10, (July 2010).

[17]

Peter Stone and Sarit Kraus, 'To teach or not to teach? Decision making under uncertainty in ad hoc teams', in AAMAS '10, (May 2010).

[18]

Richard S. Sutton and Andrew G. Barto, Reinforcement Learning: An Introduction, MIT Press, Cambridge, MA, USA, 1998.

[19]

M. Tambe, 'Towards flexible teamwork', Journal of Artificial Intelligence Research, 7, 83-124, (1997).

[20]

Feng Wu, Shlomo Zilberstein, and Xiaoping Chen, 'Online planning for ad hoc autonomous agent teams', in IJCAI, (2011).

Cited By

Nikolaidis SKwon MForlizzi JSrinivasa S(2018)Planning with Verbal Communication for Human-Robot CollaborationACM Transactions on Human-Robot Interaction10.1145/32033057:3(1-21)Online publication date: 16-Nov-2018
https://dl.acm.org/doi/10.1145/3203305
Chen MNikolaidis SSoh HHsu DSrinivasa SKanda TŜabanović SHoffman GTapus A(2018)Planning with Trust for Human-Robot CollaborationProceedings of the 2018 ACM/IEEE International Conference on Human-Robot Interaction10.1145/3171221.3171264(307-315)Online publication date: 26-Feb-2018
https://dl.acm.org/doi/10.1145/3171221.3171264
Chakraborty MChua KDas SJuba B(2017)Coordinated versus decentralized exploration in multi-agent multi-armed banditsProceedings of the 26th International Joint Conference on Artificial Intelligence10.5555/3171642.3171667(164-170)Online publication date: 19-Aug-2017
https://dl.acm.org/doi/10.5555/3171642.3171667
Show More Cited By

Recommendations

Communicating with unknown teammates
AAMAS '14: Proceedings of the 2014 international conference on Autonomous agents and multi-agent systems

Past research has investigated a number of methods for coordinating teams of agents, but, with the growing number of sources of agents, it is likely that agents will encounter teammates that do not share their coordination methods. Therefore, it is ...
Communicating Intentions for Coordination with Unknown Teammates: (Extended Abstract)
AAMAS '16: Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems

Ad hoc multiagent teamwork introduces the challenge of coordinating with a variety of potential teammates, including teammates with unknown behavior. We examine the communication of policy information for enhanced coordination between such agents. The ...
Learning to Cooperate with Completely Unknown Teammates
Progress in Artificial Intelligence
Abstract
A key goal of ad hoc teamwork is to develop a learning agent that cooperates with unknown teams, without resorting to any pre-coordination protocol. Despite a vast number of ad hoc teamwork algorithms in the literature, most of them cannot address ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Guide Proceedings

ECAI'14: Proceedings of the Twenty-first European Conference on Artificial Intelligence

August 2014

1232 pages

ISBN:9781614994183

Editors:
Torsten Schaub
University of Potsdam, Germany
,
Gerhard Friedrich
University of Klagenfurt, Austria
,
Barry O'Sullivan
University College Cork, Ireland

Sponsors

University of Potsdam: University of Potsdam
Springer
Artificial Intelligence Journal
IOS Press: IOS Press
CSKI: Czech Society for Cybernetics and Informatics

Publisher

IOS Press

Netherlands

Publication History

Published: 18 August 2014

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

5
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 24 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Nikolaidis SKwon MForlizzi JSrinivasa S(2018)Planning with Verbal Communication for Human-Robot CollaborationACM Transactions on Human-Robot Interaction10.1145/32033057:3(1-21)Online publication date: 16-Nov-2018
https://dl.acm.org/doi/10.1145/3203305
Chen MNikolaidis SSoh HHsu DSrinivasa SKanda TŜabanović SHoffman GTapus A(2018)Planning with Trust for Human-Robot CollaborationProceedings of the 2018 ACM/IEEE International Conference on Human-Robot Interaction10.1145/3171221.3171264(307-315)Online publication date: 26-Feb-2018
https://dl.acm.org/doi/10.1145/3171221.3171264
Chakraborty MChua KDas SJuba B(2017)Coordinated versus decentralized exploration in multi-agent multi-armed banditsProceedings of the 26th International Joint Conference on Artificial Intelligence10.5555/3171642.3171667(164-170)Online publication date: 19-Aug-2017
https://dl.acm.org/doi/10.5555/3171642.3171667
Chocron PSchorlemmer MLarson KWinikoff MDas SDurfee E(2017)Vocabulary Alignment in Openly Specified InteractionsProceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems10.5555/3091125.3091275(1064-1072)Online publication date: 8-May-2017
https://dl.acm.org/doi/10.5555/3091125.3091275
Chocron PSchorlemmer M(2016)Attuning ontology alignments to semantically heterogeneous multi-agent interactionsProceedings of the Twenty-second European Conference on Artificial Intelligence10.3233/978-1-61499-672-9-871(871-879)Online publication date: 29-Aug-2016
https://dl.acm.org/doi/10.3233/978-1-61499-672-9-871

View Options

View options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents