Fuzzy PID controller design using Q-learning algorithm with a manipulated reward function

Vahid Tavakol Aghaei, Ahmet Onat, Ibrahim Eksin, Mujde Guzelkaya

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

12 Citations (Scopus)


In this paper we propose a manipulated reward function for the Q-learning algorithm which is a reinforcement learning technique and utilize the proposed algorithm to tune the parameters of the input-output membership functions of fuzzy logic controllers. The use of a reward signal to formalize the idea of a goal is one of the most distinctive features of reinforcement learning. To improve both the performance and convergence criteria of the mentioned algorithm we propose a fuzzy structure for the reward function. In order to demonstrate the effectiveness of the algorithm we apply it to two second order linear systems with and without time delay and finally a nonlinear system will be examined.

Original languageEnglish
Title of host publication2015 European Control Conference, ECC 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages6
ISBN (Electronic)9783952426937
Publication statusPublished - 16 Nov 2015
EventEuropean Control Conference, ECC 2015 - Linz, Austria
Duration: 15 Jul 201517 Jul 2015

Publication series

Name2015 European Control Conference, ECC 2015


ConferenceEuropean Control Conference, ECC 2015

Bibliographical note

Publisher Copyright:
© 2015 EUCA.


Dive into the research topics of 'Fuzzy PID controller design using Q-learning algorithm with a manipulated reward function'. Together they form a unique fingerprint.

Cite this