Deep Reinforcement Learning for Multi-Domain Dialogue Systems
Artificial Intelligence
2021-05-10 v1 Computation and Language
Machine Learning
Abstract
Standard deep reinforcement learning methods such as Deep Q-Networks (DQN) for multiple tasks (domains) face scalability problems. We propose a method for multi-domain dialogue policy learning---termed NDQN, and apply it to an information-seeking spoken dialogue system in the domains of restaurants and hotels. Experimental results comparing DQN (baseline) versus NDQN (proposed) using simulations report that our proposed method exhibits better scalability and is promising for optimising the behaviour of multi-domain dialogue systems.
Cite
@article{arxiv.1611.08675,
title = {Deep Reinforcement Learning for Multi-Domain Dialogue Systems},
author = {Heriberto Cuayáhuitl and Seunghak Yu and Ashley Williamson and Jacob Carse},
journal= {arXiv preprint arXiv:1611.08675},
year = {2021}
}
Comments
NIPS Workshop on Deep Reinforcement Learning, 2016