NTRS - NASA Technical Reports Server

Back to Results
Structure identification in fuzzy inference using reinforcement learningIn our previous work on the GARIC architecture, we have shown that the system can start with surface structure of the knowledge base (i.e., the linguistic expression of the rules) and learn the deep structure (i.e., the fuzzy membership functions of the labels used in the rules) by using reinforcement learning. Assuming the surface structure, GARIC refines the fuzzy membership functions used in the consequents of the rules using a gradient descent procedure. This hybrid fuzzy logic and reinforcement learning approach can learn to balance a cart-pole system and to backup a truck to its docking location after a few trials. In this paper, we discuss how to do structure identification using reinforcement learning in fuzzy inference systems. This involves identifying both surface as well as deep structure of the knowledge base. The term set of fuzzy linguistic labels used in describing the values of each control variable must be derived. In this process, splitting a label refers to creating new labels which are more granular than the original label and merging two labels creates a more general label. Splitting and merging of labels directly transform the structure of the action selection network used in GARIC by increasing or decreasing the number of hidden layer nodes.
Document ID
Document Type
Conference Paper
Berenji, Hamid R. (Sterling Software Moffett Field, CA., United States)
Khedkar, Pratap (California Univ. Berkeley., United States)
Date Acquired
September 6, 2013
Publication Date
January 1, 1993
Publication Information
Publication: NASA. Johnson Space Center, Proceedings of the Third International Workshop on Neural Networks and Fuzzy Logic, Volume 1
Subject Category
Distribution Limits
Work of the US Gov. Public Use Permitted.