A Neuro - Control Design Based on Fuzzy Reinforcement Learning { Private } Report

This paper describes a neuro-control fuzzy critic design procedure based on reinforcement learning. An important component of the proposed intelligent control configuration is the fuzzy credit assignment unit which acts as a critic, and through fuzzy implications provides adjustment mechanisms to the main controller. The main controller is the neuro-control unit consisting of a full interconnected multi-layer feed forward neural network. The neural network adjusts its weights according to the credit assigned to its output by the fuzz credit assignment unit, using back propagation algorithms. The fuzzy credit assignment unit comprises a fuzzy system with the appropriate fuzzification, knowledge base and defuzzification components. When an external reinforcement signal (a failure signal) is received, sequences of control actions are evaluated and modified by the action applier unit. The desirable ones instruct the neuro-control unit to adjust its weights and are simultaneously stored in the memory unit during the training phase. In response to the internal reinforcement signal (set point threshold deviation), the stored information is retrieved by the action applier unit and utilized for readjustment of the neural network during the recall phase. In order to illustrate the effectiveness of the proposed technique, the controller is tested on a cart-pole balancing problem. Results of extensive simulation studies show a very good performance in comparison with other intelligent control methods.