Learning Multi-Goal Dialogue Strategies Using Reinforcement Learning with Reduced State-Action Spaces

Heriberto Cuayáhuitl, Steve Renals, Oliver Lemon, Hiroshi Shimodaira

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Learning dialogue strategies using the reinforcement learning framework is problematic due to its expensive computational cost. In this paper we propose an algorithm that reduces a state-action space to one which includes only valid state-actions. We performed experiments on full and reduced spaces using three systems (with 5, 9 and 20 slots) in the travel domain using a simulated environment. The task was to learn multi-goal dialogue strategies optimizing single and multiple confirmations. Average results using strategies learnt on reduced spaces reveal the following benefits against full spaces: 1) less computer memory (94% reduction), 2) faster learning (93% faster convergence) and better performance (8.4% less time steps and 7.7% higher reward).
Original languageEnglish
Title of host publicationInterspeech 2006 - ICSLP
Subtitle of host publicationNinth International Conference on Spoken Language Processing, Proceedings of the
PublisherISCA
Publication statusPublished - 2006
EventNinth International Conference on Spoken Language Processing (INTERSPEECH 2006 - ICSLP) - Pittsburgh, PA, United States
Duration: 17 Sept 200621 Sept 2006

Conference

ConferenceNinth International Conference on Spoken Language Processing (INTERSPEECH 2006 - ICSLP)
Country/TerritoryUnited States
CityPittsburgh, PA
Period17/09/0621/09/06

Fingerprint

Dive into the research topics of 'Learning Multi-Goal Dialogue Strategies Using Reinforcement Learning with Reduced State-Action Spaces'. Together they form a unique fingerprint.

Cite this