Login / Signup
Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management.
Pei-Hao Su
Pawel Budzianowski
Stefan Ultes
Milica Gasic
Steve J. Young
Published in:
CoRR (2017)
Keyphrases
</>
reinforcement learning
dialogue management
machine learning
semi supervised
optimal control
learning algorithm
computational complexity
sufficient conditions
dialogue system
actor critic