Modular Fuzzy-Reinforcement Learning Approach With Internal Model Capabilities for Multiagent Systems

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Volumn 34, Issue 2, 2004, Pages 1210-1223

  Kaya, Mehmet ^a   Alhajj, Reda ^b  

^a FIRAT UNIVERSITY   (Turkey)

^b UNIVERSITY OF CALGARY   (Canada)

Author keywords

Fuzziness; Internal model; Modular approach; Multiagent systems; Parallel update; Reinforcement learning

Indexed keywords

ARTIFICIAL INTELLIGENCE; COMPUTATION THEORY; COMPUTER ARCHITECTURE; CONVERGENCE OF NUMERICAL METHODS; FAULT TOLERANT COMPUTER SYSTEMS; LEARNING SYSTEMS; MATHEMATICAL MODELS; MULTI AGENT SYSTEMS;

FUZZINESS; INTERNAL MODELS; MODULAR APPROACH; PARALLEL UPDATE; REINFORCEMENT LEARNING;

FUZZY SETS;

EID: 1842535228     PISSN: 10834419     EISSN: None     Source Type: Journal    
DOI: 10.1109/TSMCB.2003.821869     Document Type: Article

References (34)

1. P. Stone and M. Veloso, "Multiagent systems: a survey from a machine learning perspective," Auton. Robots, vol. 8, no. 3, 2000.
2. S. Benson, "Reacting, planning and learning in an autonomous agent," Ph.D. dissertation, Comput. Sci. Dept., Stanford Univ., Stanford, CA, 1995.
3. M. L. Littman, "Markov games as a framework for multiagent reinforcement learning," in Proc. Int. Conf. Machine Learning, San Francisco, CA, 1994, pp. 157-163.
4. T. W. Sandholm and R. H. Crites, "Multiagent reinforcement learning in the iterated prisoner's dilemma," Biosystems, vol. 37, pp. 147-166, 1995.
5. M. Tan, "Multi-agent reinforcement learning: independent vs. cooperative agents," in Proc. Int. Conf. Machine Learning, 1993, pp. 330-337.
6. S. Whitehead, J. Karlsson, and J. Tenenberg, "Learning multiple goal behavior via task decomposition and dynamic policy merging," in Robot Learn.. Norwell, MA: Kluwer, 1993.
7. N. Ono and K. Fukomoto, "Multi-agent reinforcement learning: a modular approach," in Proc. IEEE Int. Conf. Multi-Agent Systems, 1996, pp. 252-258.
8. K. H. Park, Y. J. Kim, and J. H. Kim, "Modular Q-learning based multiagent cooperation for robot soccer," Robot. Auton. Syst., vol. 35, pp. 109-122, 2001.
9. L. Baird, "Residual algorithms: reinforcement learning with function approximation," in Proceedings of the International Conference on Machine Learning. New York: Morgan Kaufmann, 1995.
10. R. S. Sutton, "Generalization in reinforcement learning: successful examples using sparse coarse coding," Adv. Neural Inf. Processing Syst., 1996.
11. R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction. Cambridge, MA: MIT Press, 1998.
12. L. J. Lin, "Self-improving reactive agents based on reinforcement learning, planning and teaching," Mach. Learn., vol. 8, pp. 293-321, 1992.
13. P. Touzet, "Neural reinforcement learning for behavior synthesis," in Proc. CESA, IMACS Multiconf., Lille, France, July 1996.
14. O. Abul, F. Polat, and R. Alhajj, "Multiagent reinforcement learning using function approximation," IEEE Trans. Syst., Man, Cybern. C, vol. 30, pp. 485-497, Aug. 2000.
15. F. Polat and A. Guvenir, "A conflict resolution based decentralized multi-agent problem solving model," in Artificial Social Systems. New York: Springer-Verlag, 1994.
16. H. R. Beon and H. S. Cho, "A sensor-based navigation for a mobile robot using fuzzy-logic and reinforcement learning," IEEE Trans. Syst., Man, Cybern., vol. 25, pp. 464-477, June 1995.
17. N. H. C. Yung and C. Ye, "An intelligent mobile vehicle navigator based on fuzzy logic and reinforcement learning," IEEE Trans. Syst., Man, Cybern. B, vol. 29, pp. 314-321, Apr. 1999.
18. H. Berenji and D. Vengerov, "Cooperation and coordination between fuzzy reinforcement learning agents in continuous state partially observable Markov decision processes," in Proc. IEEE Int. Conf. Fuzzy Systems, vol. 2, Seoul, South Korea, 1999, pp. 621-627.
19. _, "Advantage of cooperation between reinforcement learning agents in difficult stochastic problems," in Proc. IEEE Int. Conf. Fuzzy Systems, vol. 2, San Antonio, TX, 2000, pp. 871-876.
20. M. Kaya and A. Kiliç, "Fuzzy-reinforcement learning in cooperative multi-agent systems," in Proc. Int. Symp. Computer and Information Sciences, Antalya, Turkey, 2001.
21. J. Hu and M. P. Wellman, "Multiagent reinforcement learning: theoretical framework and an algorithm," in Proc. Int. Conf. Machine Learning, 1998, pp. 242-250.
22. Y. Nagayuki, S. Ishii, and K. Doya, "Multi-agent reinforcement learning: an approach based on the other agent's internal model," in Proc. IEEE Int. Conf. Multi-Agent Systems, Boston, MA, 2000, pp. 215-221.
23. M. Kaya and A. Arslan, "Learning faster in cooperative multi-agent systems," in Proc. Symp. Adaptive Agents and Multi-Agent Systems, York, U.K., Mar. 2001, pp. 85-89.
24. A. Kiliç, M. Kaya, and A. Arslan, "Finding sub-optimal policies faster in multi-agent systems: FQ-learning," in Proc. Int. Conf. Intelligent Autonomous Systems, Marina del Rey, CA, 2002.
25. L. P. Kaelbling, M. L. Littman, and A. W. Moore, "Reinforcement learning: a survey," Artif. Intell. Res., vol. 4, pp. 237-285, 1996.
26. L. P. Kaelbling et al., "Planning and acting in partially observable stochastic domains," Artif. Intell., vol. 101, 1998.
27. N. Meuleau et al., "Learning finite-state controllers for partially observable environments," in Proc. Int. Conf. Uncertainty in Artificial Intelligence, 1999.
28. D. J. C. MacKay, "Introduction to Monte Carlo methods," in Learning in Graphical Models, M. I. Jordan, Ed. Cambridge, MA: MIT Press, 1999, pp. 175-204.
29. C. J. C. H. Watkins and P. Dayan, "Technical note: Q-learning," Mach. Learn., vol. 8, pp. 279-292, 1992.
30. N. Ono and K. Fukomoto, "A modular approach to multi-agent reinforcement learning," in Distributed Artificial Intelligence Meets Machine Learning - Learning in Multiagent Environments, G. Weiss, Ed. Berlin, Germany: Springer-Verlag, 1997, vol. 1221, pp. 25-39.
31. P. Dayan and G. E. Hinton, "Feudal reinforcement learning," Adv. Neural Inf. Processing Syst., vol. 5, pp. 271-278, 1993.
32. S. P. Singh, "Reinforcement learning with a hierarchy of abstract models," in Proc. Nat. Conf. Artificial Intelligence, 1992, pp. 202-207.
33. _, "Learning to solve Markov decision processes," Ph.D. dissertation, Dept. Comput. Sci., Univ. Massachusetts, Boston, MA, 1994.
34. L. Jouffe, "Fuzzy inference systems learning by reinforcement methods," IEEE Trans. Syst., Man, Cybern., vol. 28, no. 3, pp. 338-355, Aug. 1998.