Chowdhury, M.M., and Li, Y. (1998) Learning fuzzy control by evolutionary and advantage reinforcements. International Journal of Intelligent Systems, 13(10-11), pp. 949-974. (doi:10.1002/(SICI)1098-111X(199810/11)13:10/11<949::AID-INT5>3.0.CO;2-Z)
Full text not currently available from Enlighten.
In this paper, evolutionary and dynamic programming-based reinforcement learning techniques are combined to form an unsupervised learning scheme for designing autonomous optimal fuzzy logic control systems. A ‘‘messy genetic algorithm’’ and an ‘‘advantage learning’’ scheme are first compared as reinforcement learning paradigms. The messy genetic algorithm enables flexible coding of a fuzzy structure for global optimization, resulting in a coarsely optimized feedforward-type neurofuzzy structure. Local pruning and fine tuning of the neurofuzzy system is then achieved effectively by advantage learning by directly interacting with the environment without the use of a supervisor. The methodology is illustrated and tested in detail through application to two nonlinear control systems.
|Keywords:||fuzzy control, neural networks, genetic algorithms, evolutionary computation.|
|Glasgow Author(s) Enlighten ID:||Li, Professor Yun|
|Authors:||Chowdhury, M.M., and Li, Y.|
|Subjects:||T Technology > T Technology (General)|
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Q Science > QA Mathematics
|College/School:||College of Science and Engineering > School of Engineering > Electronics and Nanoscale Engineering|
|Research Group:||Intelligent Systems|
|Journal Name:||International Journal of Intelligent Systems|