Deep reinforcement learning for multi-domain dialogue systems

Cuayahuitl, Heriberto, Yu, Seunghak, Williamson, Ashley and Carse, Jacob (2016) Deep reinforcement learning for multi-domain dialogue systems. In: NIPS Workshop on Deep Reinforcement Learning, 9 Dec 2016, Barcelona, Spain.

Full content URL:


Item Type:Conference or Workshop contribution (Poster)
Item Status:Live Archive


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.

Keywords:Deep Reinforcement Learning, (Spoken) Dialogue Systems
Subjects:G Mathematical and Computer Sciences > G700 Artificial Intelligence
Divisions:College of Science > School of Computer Science
Related URLs:
ID Code:25935
Deposited On:02 Feb 2017 14:54

Repository Staff Only: item control page