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 language | English |
---|---|
Title of host publication | Interspeech 2006 - ICSLP |
Subtitle of host publication | Ninth International Conference on Spoken Language Processing, Proceedings of the |
Publisher | ISCA |
Publication status | Published - 2006 |
Event | Ninth International Conference on Spoken Language Processing (INTERSPEECH 2006 - ICSLP) - Pittsburgh, PA, United States Duration: 17 Sept 2006 → 21 Sept 2006 |
Conference
Conference | Ninth International Conference on Spoken Language Processing (INTERSPEECH 2006 - ICSLP) |
---|---|
Country/Territory | United States |
City | Pittsburgh, PA |
Period | 17/09/06 → 21/09/06 |