Article Structure
Abstract
We use single-agent and multi-agent Reinforcement Learning (RL) for learning dialogue policies in a resource allocation negotiation scenario.
Introduction
The dialogue policy of a dialogue system decides on which actions the system should perform given a particular dialogue state (i.e., dialogue context).
Related Work
Most research in RL for dialogue management has been done in the framework of slot-filling applications such as restaurant recommendations (Lemon et a1., 2006; Thomson and Young, 2010; Gasic et al., 2012; Daubigney et a1., 2012), flight reservations (Henderson et a1., 2008), sightseeing recommendations (Misu et al., 2010), appointment scheduling (Georgila et al., 2010), etc.
Single-Agent vs. Multi-Agent Reinforcement Learning
Reinforcement Learning (RL) is a machine learning technique used to learn the policy of an agent, i.e., which action the agent should perform given its current state (Sutton and Barto, 1998).
Domain and Experimental Setup
Our domain is a resource allocation negotiation scenario.
