Simulation of dialogue management for learning dialogue strategy using learning automata

Modeling the behavior of the dialogue management in the design of a spoken dialogue system using statistical methodologies is currently a growing research area. This paper presents a work on developing an adaptive learning approach to optimize dialogue strategy. The problem of dialogue management can be formalized as a sequential decision making under uncertainty whose underlying probabilistic structure has a Markov Chain. A variety of data driven algorithms for finding the optimal dialogue strategy is available within Markov Decision Process which is based on reinforcement learning. However the local reward function is typically set as static and there exist a dilemma in engaging the type of exploration versus exploitation. Hence we present an online policy learning algorithm using learning automata for optimizing dialogue strategy which improves the naturalness of human-computer interaction that combines fast and accurate convergence with low computational complexity.