Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management

Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management Pei-Hao Su author Paweł Budzianowski author Stefan Ultes author Milica Gašić author Steve Young author 2017-08 text Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue Kristiina Jokinen editor Manfred Stede editor David DeVault editor Annie Louis editor Association for Computational Linguistics Saarbrücken, Germany conference publication su-etal-2017-sample 10.18653/v1/W17-5518 https://aclanthology.org/W17-5518/ 2017-08 147 157