Article

Ad hoc autonomous agent teams: collaboration without pre-coordination

Authors:

Gal A. Kaminka,

Jeffrey S. RosenscheinAuthors Info & Claims

AAAI'10: Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence

Pages 1504 - 1509

Published: 11 July 2010 Publication History

Abstract

As autonomous agents proliferate in the real world, both in software and robotic settings, they will increasingly need to band together for cooperative activities with previously unfamiliar teammates. In such ad hoc team settings, team strategies cannot be developed a priori. Rather, an agent must be prepared to cooperate with many types of teammates: it must collaborate without pre-coordination. This paper challenges the AI community to develop theory and to implement prototypes of ad hoc team agents. It defines the concept of ad hoc team agents, specifies an evaluation paradigm, and provides examples of possible theoretical and empirical approaches to challenge. The goal is to encourage progress towards this ambitious, newly realistic, and increasingly important research goal.

References

[1]

Brafman, R. I., and Tennenholtz, M. 1996. On partially controlled multi-agent systems. JAIR 4:477-507.

[2]

Carmel, D., and Markovitch, S. 1995. Opponent modeling in a multi-agent system. In Sen, S., ed., IJCAI-95 Workshop on Adaptation and Learning in Multiagent Systems, 8-13.

[3]

Carrbery, S. 2001. Techniques for plan recognition. User Modeling and User-Adapted Interaction 11:31-48.

[4]

Chalupsky, H.; Gil, Y.; Knoblock, C.; Lerman, K.; Oh, J.; Pynadath, D.; Russ, T.; and Tambe, M. 2001. Electric elves: Applying agent technology to support human organizations. In IAAI-01.

[5]

Claus, C., and Boutilier, C. 1998. The dynamics of reinforcement learning in cooperative multiagent systems. In AAAI-98, 746-752. AAAI Press.

[6]

Decker, K. S., and Lesser, V. R. 1995. Designing a family of coordination algorithms. In ICMAS-95, 73-80. Menlo Park, California: AAAI Press.

[7]

Grosz, B. J., and Kraus, S. 1996. Collaborative plans for complex group actions. AIJ 86:269-358.

[8]

Just, J.; Cornwell, M.; and Huhns, M. 2004. Agents for establishing ad hoc cross-organizational teams. In IEEE/WIC/ACM International Conference on Intelligent Agent Technology, 526-30.

[9]

Kildare, R. 2004. Ad-hoc online teams as complex systems: agents that cater for team interaction rules. In Proceedings of the 7th Asia-Pacific Conference on Complex Systems.

[10]

Leyton-Brown, K., and Shoham, Y. 2008. Essentials of Game Theory: A Concise, Multidisciplinary Introduction. Synthesis Lectures on Artificial Intelligence and Machine Learning. Morgan and Claypool Publishers.

[11]

Lochbaum, K. E. 1991. An algorithm for plan recognition in collaborative discourse. In ACL, 33-38.

[12]

Oshrat, Y.; Lin, R.; and Kraus, S. 2009. Facing the challenge of human-agent negotiations via effective general opponent modeling. In AAMAS-09, 377-384.

[13]

Panait, L., and Luke, S. 2005. Cooperative multi-agent learning: The state of the art. AAMAS-05 11:387-434.

[14]

Robbins, H. 1952. Some aspects of the sequential design of experiments. Bulletin American Mathematical Society 55:527-535.

[15]

Rosenfeld, A.; Kaminka, G. A.; Kraus, S.; and Shehory, O. 2008. A study of mechanisms for improving robotic group performance. AIJ 172(6-7):633-655.

[16]

Sidner, C. L. 1985. Plan parsing for intended response recognition in discourse. Computational Intelligence 1(1).

[17]

Stone, P., and Kraus, S. 2010. To teach or not to teach? decision making under uncertainty in ad hoc teams. In AAMAS-10. International Foundation for Autonomous Agents and Multiagent Systems.

[18]

Stone, P., and Veloso, M. 1999. Task decomposition, dynamic role assignment, and low-bandwidth communication for real-time strategic teamwork. AIJ 110(2):241-273.

[19]

Stone, P., and Veloso, M. 2000. Multiagent systems: A survey from a machine learning perspective. Autonomous Robots 8(3):345-383.

[20]

Stone, P.; Riley, P.; and Veloso, M. 2000. Defining and using ideal teammate and opponent models. In IAAI-00.

[21]

Sycara, K.; Decker, K.; Pannu, A.; Williamson, M.; and Zeng., D. 1996. Distributed intelligent agents. IEEE Expert 11(6).

[22]

Tambe, M. 1997. Towards flexible teamwork. JAIR 7:81-124.

[23]

Vidal, J. M., and Durfee, E. H. 1995. Recursive agent modeling using limited rationality. In ICMAS-95, 125-132. AAAI/MIT press.

Cited By

Fosong ERahman ACarlucho IAlbrecht SDastani MSichman JAlechina NDignum V(2024)Learning Complex Teamwork Tasks using a Given Sub-task DecompositionProceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems10.5555/3635637.3662911(598-606)Online publication date: 6-May-2024
https://dl.acm.org/doi/10.5555/3635637.3662911
Yan XGuo JLou XWang JZhang HDu YOh ANaumann TGloberson ASaenko KHardt MLevine S(2023)An efficient end-to-end training approach for zero-shot human-AI coordinationProceedings of the 37th International Conference on Neural Information Processing Systems10.5555/3666122.3666241(2636-2658)Online publication date: 10-Dec-2023
https://dl.acm.org/doi/10.5555/3666122.3666241
Szot AJain UBatra DKira ZDesai RRai AKrause ABrunskill ECho KEngelhardt BSabato SScarlett J(2023)Adaptive coordination in social embodied rearrangementProceedings of the 40th International Conference on Machine Learning10.5555/3618408.3619796(33365-33380)Online publication date: 23-Jul-2023
https://dl.acm.org/doi/10.5555/3618408.3619796
Show More Cited By

Index Terms

Ad hoc autonomous agent teams: collaboration without pre-coordination
1. Computer systems organization
  1. Embedded and cyber-physical systems
    1. Robotics
2. Computing methodologies
  1. Artificial intelligence
    1. Distributed artificial intelligence
      1. Multi-agent systems
    2. Planning and scheduling
      1. Robotic planning

Index terms have been assigned to the content through auto-classification.

Recommendations

Towards heterogeneous agent teams
Mutli-agents systems and applications

Agent integration architectures enable a heterogeneous, distributed set of agents to work together to address problems of greater complexity than those addressed by the individual agents themselves. Unfortunately, integrating software agents and humans ...
Attack-resistant cooperation stimulation in autonomous ad hoc networks

In autonomous ad hoc networks, nodes usually belong to different authorities and pursue different goals. In order to maximize their own performance, nodes in such networks tend to be selfish, and are not willing to forward packets for the benefits of ...
Towards Heterogeneous Agent Teams
EASSS '01: Selected Tutorial Papers from the 9th ECCAI Advanced Course ACAI 2001 and Agent Link's 3rd European Agent Systems Summer School on Multi-Agent Systems and Applications

Agent integration architectures enable a heterogeneous, distributed set of agents to work together to address problems of greater complexity than those addressed by the individual agents themselves. Unfortunately, integrating software agents and humans ...

Comments

Information & Contributors

Information

Published In

cover image Guide Proceedings

AAAI'10: Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence

July 2010

1970 pages

Publisher

AAAI Press

Publication History

Published: 11 July 2010

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

45
Total Citations
View Citations
0
Total Downloads

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

Reflects downloads up to 26 Jul 2024

Other Metrics

View Author Metrics

Citations

Cited By

Fosong ERahman ACarlucho IAlbrecht SDastani MSichman JAlechina NDignum V(2024)Learning Complex Teamwork Tasks using a Given Sub-task DecompositionProceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems10.5555/3635637.3662911(598-606)Online publication date: 6-May-2024
https://dl.acm.org/doi/10.5555/3635637.3662911
Yan XGuo JLou XWang JZhang HDu YOh ANaumann TGloberson ASaenko KHardt MLevine S(2023)An efficient end-to-end training approach for zero-shot human-AI coordinationProceedings of the 37th International Conference on Neural Information Processing Systems10.5555/3666122.3666241(2636-2658)Online publication date: 10-Dec-2023
https://dl.acm.org/doi/10.5555/3666122.3666241
Szot AJain UBatra DKira ZDesai RRai AKrause ABrunskill ECho KEngelhardt BSabato SScarlett J(2023)Adaptive coordination in social embodied rearrangementProceedings of the 40th International Conference on Machine Learning10.5555/3618408.3619796(33365-33380)Online publication date: 23-Jul-2023
https://dl.acm.org/doi/10.5555/3618408.3619796
Ma MLiu JSokota SKleiman-Weiner MFoerster JKrause ABrunskill ECho KEngelhardt BSabato SScarlett J(2023)Learning intuitive policies using action featuresProceedings of the 40th International Conference on Machine Learning10.5555/3618408.3619381(23358-23372)Online publication date: 23-Jul-2023
https://dl.acm.org/doi/10.5555/3618408.3619381
Xu SWang HWu YKoyejo SMohamed SAgarwal ABelgrave DCho KOh A(2022)Grounded reinforcement learningProceedings of the 36th International Conference on Neural Information Processing Systems10.5555/3600270.3600815(7504-7519)Online publication date: 28-Nov-2022
https://dl.acm.org/doi/10.5555/3600270.3600815
Papoudakis GChristianos FAlbrecht SRanzato MBeygelzimer ADauphin YLiang PVaughan J(2021)Agent modelling under partial observability for deep reinforcement learningProceedings of the 35th International Conference on Neural Information Processing Systems10.5555/3540261.3541730(19210-19222)Online publication date: 6-Dec-2021
https://dl.acm.org/doi/10.5555/3540261.3541730
Siu HPeña JZhou YChen ELopez VPalko KChang KAllen RRanzato MBeygelzimer ADauphin YLiang PVaughan J(2021)Evaluation of human-AI teams for learned and rule-based agents in HanabiProceedings of the 35th International Conference on Neural Information Processing Systems10.5555/3540261.3541499(16183-16195)Online publication date: 6-Dec-2021
https://dl.acm.org/doi/10.5555/3540261.3541499
Strouse DMcKee KBotvinick MHughes EEverett RRanzato MBeygelzimer ADauphin YLiang PVaughan J(2021)Collaborating with humans without human dataProceedings of the 35th International Conference on Neural Information Processing Systems10.5555/3540261.3541372(14502-14515)Online publication date: 6-Dec-2021
https://dl.acm.org/doi/10.5555/3540261.3541372
Cui BHu HPineda LFoerster JRanzato MBeygelzimer ADauphin YLiang PVaughan J(2021)K-level reasoning for zero-shot coordination in HanabiProceedings of the 35th International Conference on Neural Information Processing Systems10.5555/3540261.3540889(8215-8228)Online publication date: 6-Dec-2021
https://dl.acm.org/doi/10.5555/3540261.3540889
Paleja RGhuy MArachchige NJensen RGombolay MRanzato MBeygelzimer ADauphin YLiang PVaughan J(2021)The utility of explainable AI in ad hoc human-machine teamingProceedings of the 35th International Conference on Neural Information Processing Systems10.5555/3540261.3540308(610-623)Online publication date: 6-Dec-2021
https://dl.acm.org/doi/10.5555/3540261.3540308
Show More Cited By

View Options

View options

Media

Figures

Other

Tables

View Table of Contents