Title :
Fuzzy interpolation-based Q-learning with profit sharing plan scheme
Author :
Horiuchi, Tadashi ; Fujino, Akinori ; Katai, Osamu ; Sawaragi, Tetsuo
Author_Institution :
Dept. of Precision Eng., Kyoto Univ., Japan
Abstract :
We have previously (1996) proposed fuzzy interpolation-based Q-learning where fuzzy rules are used to represent Q-function (action utility function), in order to enable us to treat continuous-valued states and actions. In this paper, we will introduce the idea of profit sharing plan (PSP) used in classifier systems into the fuzzy interpolation-based Q-learning in order to accelerate the speed of learning and will discuss its effectiveness through applications to control problems such as cart-pole balancing problems
Keywords :
fuzzy logic; interpolation; learning (artificial intelligence); action utility function; cart-pole balancing problems; classifier systems; continuous-valued actions; continuous-valued states; fuzzy interpolation-based Q-learning; profit sharing plan scheme; Acceleration; Autonomous agents; Control systems; Dynamic programming; Fuzzy control; Fuzzy systems; Inference algorithms; Learning; Neural networks; Precision engineering;
Conference_Titel :
Fuzzy Systems, 1997., Proceedings of the Sixth IEEE International Conference on
Conference_Location :
Barcelona
Print_ISBN :
0-7803-3796-4
DOI :
10.1109/FUZZY.1997.619797