Incremental Sparse Bayesian Method for Online Dialog Strategy Learning

Abstract

This paper proposes an incremental sparse Bayesian learning method to allow continuous dialog strategy learning from the interactions with real users. Since conventional reinforcement learning (RL) methods require a huge number of dialogs to reach convergence, it has been essential to use a simulated user in training dialog policies. The disadvantage of… (More)
DOI: 10.1109/JSTSP.2012.2229963

Topics

13 Figures and Tables

Slides referencing similar topics