Abstract
In the multi-agent community, the need for social deliberation appears contradictory with the need for reactivity. In this paper, we try to show that we can draw the benefits of both being reactive and being socially organized thanks to what we call “social reactivity”. In order to defend this claim, we describe a simulation experiment in which several sheepdog agents have to coordinate their effort to drive a flock of ducks towards a goal area. We implement reactive controllers for agents in the Classifier Systems formalism and we compare the performance of purely reactive, solipsistic agents which are coordinated implicitly with the performance of agents using roles. We show that our role-based agents perform better than the solipsistic ones, but because of constraints on the roles of the agents, the solipsistic controllers are more robust and more opportunistic. Then we show that, by exchanging reactively their roles, a process which can be seen as implementing a form of social deliberation, role-based agents finally outperform the solipsistic ones. Since designing by hand the rules for exchanging the roles proved dificult, we conclude by advocating the necessity of tackling the problem of letting the agents learn their own role exchange processes.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
M. Asada and H. Kitano, editors. Robocup-98: Robot Soccer World Cup II. Lectures Notes in Artificial Intelligence 1604, Springer-Verlag, 1999.
M. Asada, E. Uchibe, and K. Hosoda. Cooperative behavior acquisition for mobile robots in dynamically changing real-worlds via vision-based reinforcement learning and development. Artificial Intelligence, 110(2):275–292, 1999.
S. Behnke and R. Rojas. A hierarchy of reactive behaviors handles complexity. In M. Hannebauer, J. Wendler, and E. Pagello, editors, Balancing Reactivity and Social Deliberation in Multi-agent Systems (this volume), pages 125–136. Springer, 2001.
R. E. Bellman. Dynamic Programming. Princeton University Press, Princeton, NJ, 1957.
M. Bouzid, H. Hanna, and A.-I. Mouaddib. Deliberation levels in theoretic-decision approaches for task allocation in resource-bounded agents. In M. Hannebauer, J. Wendler, and E. Pagello, editors, Balancing Reactivity and Social Deliberation in Multi-agent Systems (this volume), pages 198–216. Springer, 2001.
A. Bredenfeld and H.-U. Kobialka. Team cooperation using dual dynamics. In M. Hannebauer, J. Wendler, and E. Pagello, editors, Balancing Reactivity and Social Deliberation in Multi-agent Systems (this volume), pages 111–124. Springer, 2001.
R. A. Brooks. Intelligence without reason. A.I. Memo 1293, Massachusetts Institute of Technology, Artificial Intelligence Laboratory, 1991.
M. Colombetti and M. Dorigo. Training agents to perform sequential behavior. Technical Report TR-93-023, International Computer Science Institute, Berkeley, 1993.
P. Gérard and O. Sigaud. YACS: Combining dynamic programming with generalization in classifier systems. In W. Stolzmann, P.-L. Lanzi, and S. W. Wilson, editors, LNAI 1996: Advances in Classifier Systems. Springer-Verlag, to appear, 2001.
P. Gérard, W. Stolzmann, and O. Sigaud. YACS: a new learning classifier system with anticipation. Journal of Soft Computing, to appear, 2001.
D. E. Goldberg. Genetic Algorithms in Search, Optimization, and Machine Learning. Addison Wesley, 1989.
J. H. Holland. Adaptation in Natural and Artificial Systems. The University of Michigan Press, 1975.
L. P. Kaelbing. An architecture for intelligent reactive systems. In J. Allen, J. Hendler, and A. Tate, editors, Readings in Planning, chapter 11, pages 713–728. Morgan Kaufmann Publishers, Inc., 1990.
M. J. Matarić. Interaction and Intelligent Behavior. PhD thesis, MIT AI Mobot Lab, 1994.
M. J. Matarić. Rewards functions for accelerated learning. In W. W. Cohen and H. Hirsch, editors, Proceedings of the Eleventh International Conference on Machine Learning, San Francisco, CA, 1994. Morgan Kaufmann Publishers.
M. Riedmiller, A. Moore, and J. Schneider. Reinforcement learning for cooperating and communicating reactive agents in electrical power grid. In M. Hannebauer, J. Wendler, and E. Pagello, editors, Balancing Reactivity and Social Deliberation in Multi-agent Systems (this volume), pages 137–149. Springer, 2001.
R. L. Riolo. Lookahead planning and latent learning in a classifier system. In From Animals to Animats: Proceedings of the First International Conference on Simulation of Adaptive Behavior, pages 316–326, Cambridge, MA, 1990. MIT Press.
O. Sigaud and P. Gérard. Using classifier systems as adaptive expert systems for control. In W. Stolzmann, P.-L. Lanzi, and S. W. Wilson, editors, LNAI 1996: Advances in Classifier Systems. Springer-Verlag, to appear, 2001.
W. Stolzmann. Anticipatory classifier systems. In J. R. Koza, W. Banzhaf, K. Chellapilla, K. Deb, M. Dorigo, D. B. Fogel, M. H. Garzon, D. E. Golberg, H. Iba, and R. Riolo, editors, Genetic Programming. Morgan Kaufmann Publishers, Inc., San Francisco, CA, 1998.
P. Stone and M. Veloso. Multiagent systems: A survey from a machine learning perspective. Technical Report CMU-CS-97-193, School of Computer Science, Carnegie Mellon University, Pittsburg, PA 15213, 1997.
P. Stone and M. Veloso. Task decomposition, dynamic role assignment, and low-bandwidth communication for real-time strategic teamwork. Artificial Intelligence, 110(2):241–273, 1999.
M. Tambe, J. Adibi, Y. al Onaizan, A. Erdem, G. A. Kaminka, S. C. Marsella, and I. Muslea. Building agent teams using an explicit teamwork model and learning. Artificial Intelligence, 110(2):215–239, 1999.
R. Vaughan, N. Stumpter, A. Frost, and S. Cameron. Robot sheepdog project achieves automatic flock control. In R. Pfeifer, B. Blumberg, J.-A. Meyer, and S. W. Wilson, editors, From Animals to Animats 5: roceedings of the Fifth International Conference on Simulation of Adaptive Behavior, pages 489–493, Cambridge, MA, 1998. MIT Press.
S. W. Wilson. ZCS, a zeroth level classifier system. Evolutionary Computation, 2(1):1–18, 1994.
S. W. Wilson. Classifier fitness based on accuracy. Evolutionary Computation, 3(2):149–175, 1995.
C. M. Witkowski. Schemes for Learning and behaviour: A New Expectancy Model. PhD thesis, Department of Computer Science, University of London, England, 1997.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sigaud, O., Gérard, P. (2001). Being Reactive by Exchanging Roles: An Empirical Study. In: Balancing Reactivity and Social Deliberation in Multi-Agent Systems. BRSDMAS 2000. Lecture Notes in Computer Science(), vol 2103. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44568-4_10
Download citation
DOI: https://doi.org/10.1007/3-540-44568-4_10
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42327-0
Online ISBN: 978-3-540-44568-5
eBook Packages: Springer Book Archive