Temporal Difference based Tuning of Fuzzy Logic Controller through Reinforcement Learning to Control an Inverted Pendulum
R. Kumar, M. J. Nigam, Sudeep Sharma, Punitkumar Bhavsar · International Journal of Intelligent Systems and Applications · 2012
This paper presents a self-tuning method of fuzzy logic controllers.The consequence part of the fuzzy log ic controller is self-tuned through the Qlearning algorithm of reinforcement learning.The off policy temporal d ifference algorithm is used for tuning which directly appro ximate the action value function which g ives the maximu m reward.In this way, the Qlearning algorith m is used for the continuous time environment.The approach considered is having the advantage of fuzzy logic controller in a way that it is robust under the environmental uncertainties and no expert knowledge is required to design the rule base of the fuzzy logic controller.