Entorno para el aprendizaje automático de estrategias de diálogo

This paper presents the design of spoken dialogue system strategies based on reinforcement learning. Many authors have recently proposed treating the dialogue system as a state sequence and the introduction of learning methods based on trial-and- error to find and optimal dialogue strategy has opened a new investigation area. This work proposes some ideas to deal with the probabilities of the simulated model, learning automatization and reinforce variables. All this issues have improved our learning model.