author = {Layla El Asri and Romain Laroche and Olivier Pietquin},
title = {Reward Function Learning for Dialogue Management},
year = {2012},
booktitle = {Proceedings of the sixth Starting Artificial Intelligence Research Symposium (STAIRS 2012)},
pages = {95 - 106},
month = {August},
address = {Montpellier (France)},
url = {https://www.haiti.cs.uni-potsdam.de/proceedings/ECAI2012/content/stairs/stairs201209.pdf},
abstract = {This paper addresses the problem of defining, from data, a reward function in a Reinforcement Learning (RL) problem. This issue is applied to the case of Spoken Dialogue Systems (SDS), which are interfaces enabling users to interact in natural language. A new methodology which, from system evaluation, apportions rewards over the systemís state space, is suggested. A corpus of dialogues is collected on-line and then evaluated by experts, assigning a numerical performance score to each dialogue according to the quality of dialogue management. The approach described in this paper infers, from these scores, a locally distributed reward function which can be used on-line. Two algorithms achieving this goal are proposed. These algorithms are tested on an SDS and it is showed that in both cases, the resulting numerical rewards are close to the performance scores and thus, that it is possible to extract relevant information from performance evaluation to optimise on- line learning.}