Title :
Reinforcement learning and tuning for neural network based fuzzy logic controller
Author :
Wu, Gengfeng ; Sun, Hongjin ; Dong, Jianquan ; Cao, Min ; Wang, Tao
Author_Institution :
Sch. of Comput. Eng. & Sci., Shanghai Univ., China
Abstract :
Proposes a reinforcement neural network based fuzzy logic controller (RNNFLC) for solving reinforcement learning and tuning problems. A simplified and effective reinforcement based learning algorithm is proposed to generate fuzzy rules automatically. A reinforcement-tuning algorithm is introduced to tune the membership function. The RNNFLC is applied to a cart-pole balancing system and shows significant improvements
Keywords :
fuzzy control; learning (artificial intelligence); neurocontrollers; position control; tuning; cart-pole balancing system; fuzzy rules; membership function; reinforcement learning; reinforcement neural network based fuzzy logic controller; Computer networks; Electronic mail; Fuzzy control; Fuzzy logic; Fuzzy neural networks; Learning; Neural networks; Signal generators; Sun; Training data;
Conference_Titel :
Signal Processing Proceedings, 2000. WCCC-ICSP 2000. 5th International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-5747-7
DOI :
10.1109/ICOSP.2000.893427
