Fuzzy modelling in reinforcement learning.
Quah, Kian Hong.
Date of Issue2006
School of Computer Engineering
A generic Fuzzy Input Takagi-Sugeno-Kang fuzzy framework (FITSK) is proposed to handle the different scenarios in this design problem. The online learning FITSK framework is extensible to both the zero-order and the first-order FITSK models. A localized version of Kalman filter algorithm is proposed for the parameter tuning of the first-order FITSK model.
DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Nanyang Technological University