@inproceedings{khouzaimi2015optimising,
author = {Khouzaimi, Hatim and Laroche, Romain and Lefevre, Fabrice},
title = {Optimising Turn-Taking Strategies With Reinforcement Learning},
booktitle = {Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)},
year = {2015},
month = {August},
abstract = {In this paper, reinforcement learning (RL) is used to learn an efficient turn-taking management model in a simulated slot-filling task with the objective of minimising the dialogue duration and maximising the completion task ratio. Turn-taking decisions are handled in a separate new module, the Scheduler. Unlike most dialogue systems, a dialogue turn is split into micro-turns and the Scheduler makes a decision for each one of them. A Fitted Value Iteration algorithm, Fitted-Q, with a linear state representation is used for learning the state to action policy. Comparison between a non-incremental and an incremental handcrafted strategies, taken as baselines, and an incremental RL-based strategy, shows the latter to be significantly more efficient, especially in noisy environments.},
url = {http://approjects.co.za/?big=en-us/research/publication/optimising-turn-taking-strategies-reinforcement-learning/},
edition = {Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)},
}