NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
Learning and tuning fuzzy logic controllers through reinforcementsThis paper presents a new method for learning and tuning a fuzzy logic controller based on reinforcements from a dynamic system. In particular, our generalized approximate reasoning-based intelligent control (GARIC) architecture (1) learns and tunes a fuzzy logic controller even when only weak reinforcement, such as a binary failure signal, is available; (2) introduces a new conjunction operator in computing the rule strengths of fuzzy control rules; (3) introduces a new localized mean of maximum (LMOM) method in combining the conclusions of several firing control rules; and (4) learns to produce real-valued control actions. Learning is achieved by integrating fuzzy inference into a feedforward neural network, which can then adaptively improve performance by using gradient descent methods. We extend the AHC algorithm of Barto et al. (1983) to include the prior control knowledge of human operators. The GARIC architecture is applied to a cart-pole balancing system and demonstrates significant improvements in terms of the speed of learning and robustness to changes in the dynamic system's parameters over previous schemes for cart-pole balancing.
Document ID
19930047273
Acquisition Source
Legacy CDMS
Document Type
Reprint (Version printed in journal)
External Source(s)
Authors
Berenji, Hamid R.
(NASA Ames Research Center Moffett Field; Sterling Software, Inc., Mountain View, CA, United States)
Khedkar, Pratap
(California Univ. Berkeley, United States)
Date Acquired
August 16, 2013
Publication Date
September 1, 1992
Publication Information
Publication: IEEE Transactions on Neural Networks
Volume: 3
Issue: 5
ISSN: 1045-9227
Subject Category
Cybernetics
Accession Number
93A31270
Funding Number(s)
CONTRACT_GRANT: NCC2-275
Distribution Limits
Public
Copyright
Other

Available Downloads

There are no available downloads for this record.
No Preview Available