Abstract
In this paper, a general fuzzy reinforcement learning (FRL) agent that can uitlise not only measurement-based information but also perception-based information by means of computing with words (CW) is proposed. By introducing fuzzy numbers and their arithmetic operations and fuzzy Lyapunov synthesis in the domain of CW, a set of stable fuzzy control rules can be derived from perception-based information. Moreover, based on a neuro-fuzzy network architecture, the fuzzy rules can be incorporated in the FRL agent to initialise its action network, critic network and evaluation feedback module so as to improve the learning. The performance and applicability of the proposed approach are illustrated through the practical implementation of learning control of an autonomous pole-balancing mobile robot.
This is a preview of subscription content, log in via an institution to check access.
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
Berenji, H.R., Khedkar, P.S.: Learning and tuning fuzzy logic controllers through reinforcements. IEEE Trans. Neural Network 3 (1992) 724–740
Klir, G.J., Yuan, B.: Fuzzy Sets and Fuzzy Logic: Theory and Applications. Pretice Hall (1995)
Li, T.-H.S., Shieh, M.-Y.: Switching-type fuzzy sliding mode control of a cart-pole system. Mechatronics 10 (2000) 91–109
Lin, C.-T., Kam, M.-C.: Adaptive fuzzy command acquisition with reinforcement learning. IEEE Trans. on Fuzzy Systems 6 (1998) 102–121
Margaliot, M. and Langholz, G.: Fuzzy Lyapunov based approach to the design of fuzzy controllers. Fuzzy Sets and Systems 106 (1999) 49–59
Slotine, J.J.E., Li, W.: Applied Nonlinear Control, Prentice Hall (1991)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press (1998)
Zadeh, L.A.: From computing with numbers to computing with words-from manipulation of measurements to manipulation of perceptions. IEEE Trans. Circuits and Systems I-45 (1999) 105–119
Xhou, C., Kanniah, J. Q. Meng: Intelligent robotic control using reinforcement learning agents with fuzzy evaluative feedback. In: Proc. of 4th FLINS. World Scientific Publisher (2000) 327–334
Zhou, C: Neuro-fuzzy gait synthesis with reinforcement learning for a biped walking robot. Soft Computing 4 (2000) 238–250
Zhou, C.: Fuzzy rules extraction for robot control using computing with words. In: Proc. 4th Asian Conference on Robotics and Its Applications, Singapore (2001)
Zhou, C., Ruan, D.: Fuzzy control rules extraction from perception-based information using computing with words. Int. J. Information Science (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhou, C., Yang, Y., Jia, X. (2001). Incorporating Perception-Based Information in Reinforcement Learning Using Computing with Words. In: Mira, J., Prieto, A. (eds) Bio-Inspired Applications of Connectionism. IWANN 2001. Lecture Notes in Computer Science, vol 2085. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45723-2_57
Download citation
DOI: https://doi.org/10.1007/3-540-45723-2_57
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42237-2
Online ISBN: 978-3-540-45723-7
eBook Packages: Springer Book Archive