Back to Results
First PageMeta Content
Dynamic programming / Stochastic control / Markov models / Expectation–maximization algorithm / Partially observable Markov decision process / Maximum likelihood / Reinforcement learning / Markov chain / Normal distribution / Statistics / Markov processes / Estimation theory


Natural Belief-Critic: a reinforcement algorithm for parameter estimation in statistical spoken dialogue systems F. Jurˇc´ıcˇ ek, B. Thomson, S. Keizer, F. Mairesse, M. Gaˇsi´c, K. Yu, and S. Young Engineering Depa
Add to Reading List

Document Date: 2010-11-01 08:12:32


Open Document

File Size: 399,46 KB

Share Result on Facebook

City

New York / Morristown / /

Company

John Wiley & Sons Inc. / MIT Press / Dialogue Systems / POMDP / /

Country

United States / United Kingdom / /

/

Facility

Cambridge University / University of Cambridge / /

IndustryTerm

reinforcement algorithm / tractable systems / random search techniques / policy optimisation algorithms / simplest systems / type g'food state / h'food / dialogue management / closed form solution / random search algorithm / food type / food / /

Organization

Cambridge University / University of Cambridge / MIT / S. Keizer / F. Mairesse / M. Gaˇsi´c / K. Yu / and S. Young Engineering Department / European Union / S. Young Engineering Department / /

Person

Let / U. Syed / J. D. Williams / /

Position

BUDS dialogue manager / Natural Actor-Critic / manager / the policy distribution / Fisher Information Matrix / manager uses / manager / the observations and system actions / system designer / Critic / manager In / proposed Natural Belief-Critic / Policy The BUDS dialogue manager / dialogue model / Natural Belief Critic / C. Bishop / Pattern Recognition and Machine Learning / dialogue manager / Natural Belief-Critic / /

PublishedMedium

Machine Learning / /

Technology

policy optimisation algorithms / Natural Belief Critic algorithm / proposed Natural Belief-Critic algorithm / NAC algorithm / random search algorithm / NBC algorithm / Machine Learning / Natural Belief-Critic algorithm / reinforcement algorithm / /

URL

www.classic-project.org / /

SocialTag