Reinforcement learning based on modular fuzzy model with gating unit

Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics

Volumn , Issue , 2008, Pages 1806-1811

  Watanabe, Toshihiko ^a   Wada, Tatsuya ^a  

^a OSAKA ELECTRO COMMUNICATION UNIVERSITY   (Japan)

Author keywords

Modular fuzzy model; Modular neural network; Neural network; Q Learning; Reinforcement learning

Indexed keywords

AUTONOMOUS MOBILE ROBOT; BEHAVIOR CONTROL; CONVENTIONAL MODELS; CONVERGENCE PROPERTIES; CURSE OF DIMENSIONALITY; FUZZY MODELS; LEARNING PARAMETERS; LEARNING PROCESS; MODULAR FUZZY MODEL; MODULAR NEURAL NETWORK; NEURAL NETWORK MODEL; NUMERICAL EXAMPLE; Q-LEARNING; Q-LEARNING ALGORITHMS; ROBOT TASKS; SENSORY STATE; TASK DECOMPOSITION;

COMPUTATIONAL EFFICIENCY; CONTROL THEORY; CONVERGENCE OF NUMERICAL METHODS; CYBERNETICS; EDUCATION; NEURAL NETWORKS; REINFORCEMENT; REINFORCEMENT LEARNING; ROBOTICS; ROBOTS; WIRELESS NETWORKS;

LEARNING ALGORITHMS;

EID: 69949174783     PISSN: 1062922X     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICSMC.2008.4811551     Document Type: Conference Paper

References (23)

1. R. S. Sutton and A. G. Barto, "Reinforcement Learning", MIT Press, 1998.
2. C. J. H. Watkins and P. Dayan, "Technical Note: Q-Leaning", Machine Learning, Vol. 8, pp. 58-68, 1992
3. J. J. Grefenstette, "Credit Assignment in Rule Discovery Systems Based on Genetic Algorithms," Machine Learning, Vol. 3, pp. 225-245, 1988.
4. K. Miyazaki, H. Kimura, and S. Kobayashi, "Theory and Application of Reinforcement Learning Based on Profit Sharing," J. of JSAI, Vol. 14, No. 5, pp. 800-807, 1999.
5. K. Miyazaki, S. Arai, and S. Kobayashi, "A Theory of Profit Sharing in Multi-agent Reinforcement Learning," J. of JSAI, Vol. 14, No. 6, pp. 1156-1164, 1999.
6. M. Benda, V. Jagannathan, and R. Dodhiawalla, "On Optimal Cooperation of Knowledge Sources," Technical Report, BCS-G2010-28, Boeing AI Center, 1985.
7. A. Ito and M. Kanabuchi, "Speeding up Multi-Agent Reinforcement Learning by Coarse-Graining of Perception-Hunter Game as an Example-," Trans. of IEICE, Vol. J84-D-1, No. 3, pp. 285-293, 2001.
8. Y. Takahashi and M. Asada, "Behavior Acquisition by Multi-Layered Reinforcement Learning," Proc, of the 1999 IEEE Int. Conf. on Syst., Man, and Cybern., pp. 716-721, 1999.
9. J. Morimoto and K Doya, "Acquisition of Stand-up Behavior by a Real Robot using Hierarchical Reinforcement Learning," Proc, of International Conference on Machine Learning, pp. 623-630, 2000.
10. nd Int. Conf. on Multi-agent Systems, pp. 252-258, AAAI Press, 1996.
11. K. Fujita and H. Matsuo, "Multi-agent Reinforcement Learning with the Partly High-Dimensional State Space," Trans, of IEICE, Vol. J88-D-1, No. 4, pp. 864-872, 2005.
12. H. Murao and S. Kitamura, "Q-Learning with Adaptive State Segmentation(QLASS)", Proc. IEEE Int. Symp. on Computational Intelligence in Robotics and Automation, pp. 179-184, 1997.
13. T. Hamagami, S. Koakutsu, and H. Hirata, "An Adjustment Method of the Number of States on Q-Learning Segmenting State Space Adaptively," Trans. of IEICE, Vol. J86-D1, No. 7, pp. 490-499, 2003.
14. H. Seki, H. Ishii, and M. Mizumoto: "On the Generalization of Single Input Rule Modules Connected Type Fuzzy Reasoning Method," Proc. of the SCIS&ISIS2006, pp. 30-34, 2006.
15. N. Yubazaki, J. Yi, M. Otani and K Hirota, "SIRMs Dynamically Connected Fuzzy Inference Model and Its Applications," Proc. IFSA '97, vol. 3, pp. 410-415, 1997.
16. Y. Takahashi and T. Watanabe: "Learning of Agent Behavior Based on Hierarchical Modular Reinforcement Learning," Proc, of the SCIS&ISIS2006, pp. 90-94, 2006.
17. T. Watanabe and Y. Takahashi, "Hierarchical Reinforcement Learning Using A Modular Fuzzy Model for Multi-Agent Problem," Proc, of the 2007 IEEE International Conference on Systems, Man, and Cybernetics, 2008.
18. R. A. Jacobs, M. I. Jordan, and A. G. Barto, "Task Decomposition through Competition in a Modular Connectionist Architecture: The What and Where Vision Tasks," Neural Computation, Vol. 3, pp. 79-87, 1991.
19. G. Auda and M. Kamel, "Modular Neural Networks: A Survey," International JournaI of Neural Systems, Vol. 9, No. 2, pp. 129-151, 1999.
20. P. Y. Glorennec, "Reinforcement Learning: Overview," Proc. of ESIT, pp. 17-35, 2000.
21. D. Gu and H. Hu, "Fuzzy Multi-Agent Cooperative Q-Learning," Proc. of the 2005 IEEE International Conferece on Information Acquisition, pp. 193-197, 2005.
22. R. S. Sutton, "Generalization in Reinforcement Learning: Successsful Examples Using Sparce Coarse Coding," Advances in Neural Information Processing Systems, Vol. 8, pp. 1038-1044, MIT Press, 1996.
23. T. Takagi and M. Sugeno: "Fuzzy Identification of Systems and Its Applications to Modeling and Control," IEEE Transaction on Systems, Man, and Cybernetics, Vol. 15, pp. 116-132, 1985.