Cited By
View all- Allen MGoldman CZilberstein S(2005)Language learning in multi-agent systemsProceedings of the 19th international joint conference on Artificial intelligence10.5555/1642293.1642594(1649-1650)Online publication date: 30-Jul-2005
Decentralized Language Learning through Acting
Pages 1006 - 1013
Abstract
This paper presents an algorithm for learning the meaning of messages communicated between agents that interact while acting optimally towards a cooperative goal. Our reinforcement-learning method is based on Bayesian filtering and has been adapted for a decentralized control process. Empirical results shed light on the complexity of the learning problem, and on factors affecting the speed of convergence. Designing intelligent agents able to adapt their mutual interpretation of messages exchanged, in order to improve overall task-oriented performance, introduces an essential cognitive capability that can upgrade the current state of the art in multi-agent and human-machine systems to the next level. Learning to communicate while acting will add to the robustness and flexibility of these systems and hence to a more efficient and productive performance.
References
[1]
{1} D.S. Bernstein, R. Givan, N. Immerman, and S. Zilberstein. The complexity of decentralized control of Markov decision processes. Mathematics of Operations Research, 27(4):819-840, 2002.
[2]
{2} Andrea Bonarini and Piera Sassaroli. Opportunistic multimodel diagnosis with imperfect models. Information Sciences , 103(1-4):161-185, 1997.
[3]
{3} S. Coradeschi and A. Saffiotti. An introduction to the anchoring problem. Robotics and Autonomous Systems, 43(2- 3):85-96, 2003.
[4]
{4} D. Davidson. Inquiries into Truth and Interpretation. Oxford UP, Oxford, England, 1984.
[5]
{5} E.H. Durfee and V.R. Lesser. Using partial global plans to coordinate distributed problem solvers. In A.H. Bond & L. Gasser, eds., Readings in Distributed Artificial Intelligence , pp. 285-293. Morgan Kaufmann, San Mateo, CA, 1988.
[6]
{6} T. Finin, Y. Labrou, and J. Mayfield. KQML as an agent communication language. In J. Bradshaw, ed., Software Agents. MIT Press, 1997.
[7]
{7} L. Firoiu, T. Oates and P. Cohen. Learning Regular Languages from Positive Evidence. In Proc. of the 20th Annual Meeting of the Cognitive Science Society, pp. 350- 355, 1998.
[8]
{8} P.J. Gmytrasiewicz, M. Summers, and D. Gopal. Toward automated evolution of agent communication languages. In Proc. of the 35th Hawaii International Conf. on System Sciences , 2002.
[9]
{9} C.V. Goldman and S. Zilberstein. Optimizing information exchange in cooperative multi-agent systems. In Proc. of the 2nd International Joint Conf. on Autonomous Agents and Multi-Agent Systems, pp. 137-144, Melbourne, Australia, 2003.
[10]
{10} C.V. Goldman and S. Zilberstein. Mechanism design for communication in cooperative systems. Proc. of the 5th Workshop on Game Theoretic and Decision Theoretic Agents, Melbourne, Australia, 2003.
[11]
{11} C.V. Goldman and S. Zilberstein. Decentralized control of cooperative systems. University of Massachusetts at Amherst, Computer Science, Technical Report 03-36, 2003.
[12]
{12} B.J. Grosz and S. Kraus. Collaborative plans for complex group action. Artificial Intelligence, 86(2):269-357, 1996.
[13]
{13} NASA. Mars Climate Orbiter Failure Board Report. Available at: ftp://ftp.hq.nasa.gov/pub/pao/ reports/1999/MCO_report.pdf, 1999.
[14]
{14} H. Putnam. The meaning of 'meaning'. In Mind, Language and Reality: Philosophical Papers, Volume 2, pp. 215-271. Cambridge University Press, Cambridge, England, 1975.
[15]
{15} D.V. Pynadath and M. Tambe. The communicative multi-agent team decision problem: Analyzing teamwork theories and models. J. of Artificial Intelligence Research, 16:389- 423, 2002.
[16]
{16} W. Van Orman Quine. Word and Object. The MIT Press, Cambridge, MA, 1960.
[17]
{17} N. Sharygina and D. Peled. A Combined Testing and Verification Approach for Software Reliability. In FME 2001, LNCS 2021, pp. 611-628, 2001.
[18]
{18} L. Steels and P. Vogt. Grounding adaptive language games in robotic agents. In Proc. of the 4th European Conf. on Artificial Life, 1997.
[19]
{19} S. Thrun, D. Fox, W. Burgard, and F. Dellaert. Robust monte carlo localization for mobile robots. Artificial Intelligence, 128:99-141, 2001.
[20]
{20} P. Vogt and H. Coumans. Investigating social interaction strategies for bootstrapping lexicon development. J. of Artificial Societies and Social Simulation, 6(1), 2003.
[21]
{21} J. Wang and L. Gasser. Mutual online concept learning for multiple agents. In Proc. of the 1st International Joint Conf. on Autonomous Agents and Multi-Agent Systems, pp. 362- 369, Bologna, Italy, 2002.
[22]
{22} H. A. Yanco. Robot Communication: Issues and Implementation. Master Thesis, MIT, 1994.
Index Terms
- Decentralized Language Learning through Acting
Recommendations
Decentralised learning in systems with many, many strategic agents
AAAI'18/IAAI'18/EAAI'18: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence and Thirtieth Innovative Applications of Artificial Intelligence Conference and Eighth AAAI Symposium on Educational Advances in Artificial IntelligenceAlthough multi-agent reinforcement learning can tackle systems of strategically interacting entities, it currently fails in scalability and lacks rigorous convergence guarantees. Crucially, learning in multi-agent systems can become intractable due to the ...
Multi-agent Reinforcement Learning for Decentralized Stable Matching
Algorithmic Decision TheoryAbstractIn the real world, people/entities usually find matches independently and autonomously, such as finding jobs, partners, roommates, etc. It is possible that this search for matches starts with no initial knowledge of the environment. We propose the ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
July 2004
487 pages
ISBN:1581138644
Sponsors
Publisher
IEEE Computer Society
United States
Publication History
Published: 19 July 2004
Check for updates
Qualifiers
- Article
Conference
AAMAS04
Sponsor:
AAMAS04: The Third International Joint Conference on Autonomous Agents and Multi-Agent Systems 2004
July 19 - 23, 2004
New York, New York
Acceptance Rates
Overall Acceptance Rate 1,155 of 5,036 submissions, 23%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- View Citations1Total Citations
- 11Total Downloads
- Downloads (Last 12 months)2
- Downloads (Last 6 weeks)0
Reflects downloads up to 13 Nov 2024
Other Metrics
Citations
Cited By
View all- Allen MGoldman CZilberstein S(2005)Language learning in multi-agent systemsProceedings of the 19th international joint conference on Artificial intelligence10.5555/1642293.1642594(1649-1650)Online publication date: 30-Jul-2005
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in