LEARNING AND TUNING FUZZY-LOGIC CONTROLLERS THROUGH REINFORCEMENTS

This 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 (a) learns and tunes a fuzzy logic controller even when only weak reinforcement, such as a binary failure signal, is available; (b) introduces a new conjunction operator in computing the rule strengths of fuzzy control rules; (c) introduces a new localized mean of maximum (LMOM) method in combining the conclusions of several firing control rules; and (d) 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, Sutton, and Anderson 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.