* This technical report is an updated version of the conference paper:
"H. Ren, W. Xu, and Y. Yan, Optimizing human-interpretable dialog management
policy using genetic algorithm, in 2015 IEEE Workshop on Automatic Speech
Recognition and Understanding (ASRU), 2015, 791-797". Experiments on policy
training via user simulator have been enriched and the reward function is
updated Access Paper or Ask Questions
Log in or sign up instantly π
π₯ Discover incredible developments in machine intelligence
π€ Quickly get code for any ML model
π Get help from authors, engineers & researchers