Abstract
Learning in a multiagent environment can help agents improve their performance. Agents, in meeting with others, can learn about the partner's knowledge and strategic behavior. Agents that operate in dynamic environments could react to unexpected events by generalizing what they have learned during a training stage'.
In this paper, we propose several learning rules for agents in a multiagent environment. Each agent acts as the teacher of its partner. The agents are trained by receiving examples from a sample space; they then go through a generalization step during which they have to apply the concept they have learned from their instructor.
Agents that learn from each other can sometimes avoid repeatedly coordinating their actions from scratch for similar problems. They will sometimes be able to avoid communication at run-time, by using learned coordination concepts.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Martin Anthony and Norman Biggs. Computational Learning Theory. Cambridge University Press, 1992.
Edmund H. Durfee. Coordination of Distributed Problem Solvers. Kluwer Academic Publishers, Boston, 1988.
N.V. Findler. Distributed control of collaborating and learning expert systems for street traffic signals. In Lewis and Stephanon, editors, IFAC Distributed Intelligence Systems, pages 125–130. Pergamon Press, 1991.
C. Goldman and J. Rosenschein. Emergent coordination through the use of cooperative state-changing rules. In AAAI94, pages 408–413, 1994.
B. Grosz and S. Kraus. Collaborative plans for group activities. In IJCAI93, pages 367–373, Chambery, France, 1993.
Michael J. Kearns and Robert E. Shapire. Efficient distribution-free learning of probabilistic concepts. In Proceedings of the 31st Anual Symposium on Foundations of Computer Science, pages 382–391, 1990.
S. Kraus and J. Wilkenfeld. Negotiations over time in a multi agent environment: Preliminary report. In IJCAI91, pages 56–61, Sydney, Australia, August 1991.
M. Littman and J. Boyan. A distributed reinforcement learning scheme for network routing. technical report CMU-CS-93-165, Carnegie Mellon University, 1993.
M. L. Littman. Markov games as a framework for multi-agent reinforcement learning. In Machine Learning 1994, pages 157–163, 1994.
Tuomas W. Sandholm and Robert H. Crites. Multiagent reinforcement learning in the iterated prisoner's dilemma. Biosystems Journal Special Issue on the Prisoner's Dilemma, submitted.
S. Sen, M. Sekaran, and J. Hale. Learning to coordinate without sharing information. In AAAI94, pages 426–431, 1994.
Y. Shoham and M. Tennenholtz. Emergent conventions in multi-agent systems: initial experimental results and observations (preliminary report). In KR92, Cambridge, Massachusetts, October 1992.
Y. Shoham and M. Tennenholtz. Co-learning and the evolution of social activity. Technical Report STAN-CS-TR-94-1511, Stanford Univ., 1994.
S. Sian. Adaptation based cooperative learning multi-agent systems. In Decentralized AI 2, pages 257–272, 1991.
Reid G. Smith. A Framework for Problem Solving in a Distributed Processing Environment. PhD thesis, Stanford University, 1978.
M. Tan. Multi-agent reinforcement learning: Independent vs. cooperative agents. In Machine Learning: Proceedings of the Tenth international conference, pages 330–337, 1993.
M. Tennenholtz and Y. Moses. On cooperation in a multi-entity model. In IJ-CAI89, pages 918–923, Detroit, Michigan, August 1989.
L. G. Valiant. A theory of the learnable. Communications of the ACM, 27(11):1134–1142, 1984.
Christopher Watkins and Peter Dayan. Technical note Q-learning. Machine Learning, 8:279–292, 1992.
Gerhard Weiß. Learning to coordinate actions in multi-agent systems. In IJCAI93, Chambery, France, 1993.
G. Zlotkin and J. S. Rosenschein. A domain theory for task oriented negotiation. In IJCAI93, pages 416–422, Chambery, France, 1993.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Goldman, C.V., Rosenschein, J.S. (1996). Mutually supervised learning in multiagent systems. In: Weiß, G., Sen, S. (eds) Adaption and Learning in Multi-Agent Systems. IJCAI 1995. Lecture Notes in Computer Science, vol 1042. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-60923-7_20
Download citation
DOI: https://doi.org/10.1007/3-540-60923-7_20
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-60923-0
Online ISBN: 978-3-540-49726-4
eBook Packages: Springer Book Archive