Abstract
This paper proposes a new Q-learning method for the case where the states (conditions) and actions of systems are assumed to be continuous. The components of Q-tables are interpolated by fuzzy inference. The initial set of fuzzy rules is made of all the combinations of conditions and actions relevant to the problem. Each rule is then associated with a value by which the Q-value of a condition/action pair is estimated. The values are revised by the Q-learning algorithm so as to make the fuzzy rule system effective. Although this framework may require a huge number of the initial fuzzy rules, we will show that considerable reduction can be done by using what we call “Condition Reduced Fuzzy Rules (CRFR)”. The antecedent part of CRFR consists of all the actions and the selected conditions, and its consequent is set to be its Q-value. Finally, experimental results show that controllers with CRFRs perform equivalently to the system with the most detailed fuzzy control rules, while the total number of parameters that have to be revised through the whole learning process is reduced and the number of the revised parameters at each step of learning is increased.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
C. Watkins and P. Dayan: Technical Note: Q-learning. Machine Learning 8-3/4 (1992) 279–292
R. S. Sutton: Generalization in Reinforcement Learning: Successful Examples Using Sparse Coarse Coding. Advances in Neural Information Processing Systems 8, MIT Press (1996)
T. Horiuchi, A. Fujino, O. Katai and T. Sawaragi: Fuzzy Interpolation-Based Q-Learning with Profit Sharing Plan Scheme. Proc. of the 6th IEEE International Conference on Fuzzy Systems (FUZZ-IEEE’97) 3 (1997) 1,707-1,712
M. Sugeno: Fuzzy Controls. Nikkan kogyo Sinbun (1988), (in Japanese)
L. J. Lin: Self-improving reactive agents based on reinforcement learning, planning and teaching. Machine Learning 8-3/4 (1992) 293–321
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kawakami, H., Katai, O., Konishi, T. (1999). A Reinforcement Learning with Condition Reduced Fuzz Rules. In: McKay, B., Yao, X., Newton, C.S., Kim, JH., Furuhashi, T. (eds) Simulated Evolution and Learning. SEAL 1998. Lecture Notes in Computer Science(), vol 1585. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48873-1_27
Download citation
DOI: https://doi.org/10.1007/3-540-48873-1_27
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-65907-5
Online ISBN: 978-3-540-48873-6
eBook Packages: Springer Book Archive