Improvement of LMI controllers of Takagi-Sugeno models via Q-learning**The authors are grateful to projects DPI2011-27845-C02-01 and DPI2013-42302-R from Spanish Government, Grant PROM-ETEOII/2013/004 from Generalitat Valenciana and Ph.D. grant SENESCYT from the Government of Ecuador.
Henry Díaz, Leopoldo Armesto, Antonio Sala · IFAC-PapersOnLine · 2016
This paper presents a preliminary attempt to bridge the conservative (shape-independent) results from guaranteed-cost LMIs and the reinforcement learning setups which learn optimal controllers from data. In this sense, the proposed approach uses an initialization based on the LMI solution and proposes an approximation of the Q-function using polynomials of the membership functions in Takagi-Sugeno models. The resulting controller is shape-dependent, that is, uses the knowledge of membership functions and data to clearly improve LMI solutions.