author = {Senthilkumar Chandramohan and Matthieu Geist and Olivier Pietquin},
title = {Sparse Approximate Dynamic Programming for Dialog Management},
year = {2010},
booktitle = {Proceedings of the 11th SIGDial Conference on Discourse and Dialogue},
publisher = {ACL},
pages = {107-115},
month = {September},
address = {Tokyo (Japan)},
url = {http://www.sigdial.org/workshops/workshop11/proc/pdf/SIGDIAL22.pdf},
abstract = {Spoken dialogue management strategy optimization by means of Reinforcement Learning (RL) is now part of the state of the art. Yet, there is still a clear mismatch between the complexity implied by the required naturalness of dialogue systems and the inability of standard RL algorithms to scale up. Another issue is the sparsity of the data available for training in the dialogue domain which can not ensure convergence of most of RL algorithms. In this paper, we propose to combine a sample-efficient generalization framework for RL with a feature selection algorithm for the learning of an optimal spoken dialogue management strategy.}