Two-Strategy reinforcement group cooperation based symbiotic evolution for TSK-type fuzzy controller design
Sheng‐Fuu Lin, Jyun-Wei Chang, Yu-Bi Hong, Yung-Chi Hsu · Artificial Intelligence Research · 2012
This paper proposes a TSK-type fuzzy controller (TFC) with a two-strategy reinforcement group cooperation based symbiotic evolution (TSR-GCSE) for solving various control problems. The TSR-GCSE proposes the two-strategy reinforcement (TSR) signal designed to improve the performance of the traditional reinforcement signal designed. Moreover, the TSR-GCSE is different from the traditional symbiotic evolution; with each population in the TSR-GCSE method is divided to several groups. Each group represents a set of the chromosomes that belongs to a fuzzy rule and can cooperate with other groups to generation the better chromosomes by using elites-base compensation crossover strategy (ECCS). The illustrative examples show that the proposed method has the better time steps and CPU times than other existing methods.