Fuzzy Q-learning with the modified fuzzy ART neural network

Proceedings - 2005 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT'05

Volumn 2005, Issue , 2005, Pages 308-315

  Ueda, Hiroaki ^a   Hanada, Naoki ^a   Kimoto, Hideaki ^a   Naraki, Takeshi ^a   Takahashi, Kenichi ^a   Miyahara, Tetsuhiro ^a  

^a HIROSHIMA CITY UNIVERSITY   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

FUZZY SETS; LEARNING SYSTEMS; NUMERICAL METHODS; PARAMETER ESTIMATION;

FUZZY ART; FUZZY Q-LEARNING;

NEURAL NETWORKS;

EID: 33846296641     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/IAT.2005.78     Document Type: Conference Paper

References (15)

1. http://www.robocup.org/.
2. G. C. Anagnostopoulos and M. Georgipoulos. New geometric concepts in fuzzy-ART and fuzzy-ARTMAP: Category regions. In Proc. of IJCNN'01, volume 1, pages 32-37, 2001.
3. H. R. Berenji and D. Vengerov. On convergence of fuzzy reinforcement learning. In Proc. of FUZZ-IEEE'01, pages 618-621, 2001.
4. M. Blume and S. C. Esener. An efficient mapping of fuzzy ART onto a neural architecture. Neural Networks, 10(3):409-411, 1997.
5. G. A. Carpenter, S. Grossberg, M. Markuzon, J. H. Reynolds, and D. B. Rosen. Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps. IEEE Trans. on Neural Networks, 3(5):698-713, 1992.
6. G. A. Carpenter, S. Grossberg, and D. B. Rosen. Fuzzy ART: fast stable learning and categorization of analog patterns by an adaptive resonance system. Neural Networks, 4(6):759-771, 1991.
7. T. Hamagami and H. Hirata. An adjustment of the number of states on q-learning segmenting state space adaptively. In Proc. of IEEE International Conference on Systems, Man, and Cybernetics, pages 3062-3067, 2003.
8. H. Handa, A. Ninomiya, T. Horiuchi, T. Konichi, and M. Baba. An incremental state-space construction based on the notion of contradiction for reinforcement learning. SCIE Trans., 38(5):469-476, 2002. (in Japanese).
9. Y.-M. Huang and S.-H. Lin. An efficient inductive learning method for object-oriented database using attribute entropy. IEEE Trans. on Knowledge and Data Engineering, 8(6):946-951, 1996.
10. H. Katagiri, K. Hirakawa, and J. Hu. Genetic network programming - application to intelligent agents -. In Proc. of IEEE International Conference on System, Man and Cybernetics, pages 3829-3834, 2000.
11. H. Kawamura, A. Ohuchi, and K. Kurumatani. Development of X-Economy System for simulation of multi-agent economy. In A. Namatame, T. Terano, and K. Kurumatani, editors, Agent-Based Approaches in Economic and Social Complex Systems, pages 188-197. IOS Press, 2002.
12. B. Mesot, E. Sanchez, C.-A. Pẽna, and A. Perez-Uribe. SOS++: Finding smart behaviors using learning and evolution. In Proc. of Artificial Life, VIII, pages 264-273, Dec. 2002.
13. R. S. Sutton and A. G. Barto. Reinforcement Learning. The MIT Press, 1998.
14. H. Ueda, N. Iwane, K. Takahashi, and T. Miyahara. Acquisition of a state transition graph using genetic network programming techniques. In Proc. of TENCON2003, pages 163-167, Oct. 2003.
15. H. Ueda, T. Yoshimori, K. Takahashi, and T. Miyahara. Categorization of continuous numeric percepts for reinforcement learning. In Proc. of TENCON2004, pages 290-293, Nov. 2004.