Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Variational denoising autoencoders and least-squares policy iteration for statistical dialogue managers

Diakoloukas Vasileios, Lygerakis Fotios, Lagoudakis Michail, Kotti Margarita

Simple record


URIhttp://purl.tuc.gr/dl/dias/A1FB74B4-8B64-46FA-B0AE-941918F57F06-
Identifierhttps://doi.org/10.1109/LSP.2020.2998361-
Identifierhttps://ieeexplore.ieee.org/document/9103219-
Languageen-
Extent5 pagesen
TitleVariational denoising autoencoders and least-squares policy iteration for statistical dialogue managersen
CreatorDiakoloukas Vasileiosen
CreatorΔιακολουκας Βασιλeioςel
CreatorLygerakis Fotiosen
CreatorΛυγερακης Φωτιοςel
CreatorLagoudakis Michailen
CreatorΛαγουδακης Μιχαηλel
CreatorKotti Margaritaen
PublisherInstitute of Electrical and Electronics Engineersen
Content SummaryThe use of Reinforcement Learning (RL) approaches for dialogue policy optimization has been the new trend for dialogue management systems. Several methods have been proposed, which are trained on dialogue data to provide optimal system response. However, most of these approaches exhibit performance degradation in the presence of noise, poor scalability to other domains, as well as performance instabilities. To overcome these problems, we propose a novel approach based on the incremental, sample-efficient Least-Squares Policy Iteration (LSPI) algorithm, which is trained on compact, fixed-size dialogue state encodings, obtained from deep Variational Denoising Autoencoders (VDAE). The proposed scheme exhibits stable and noise-robust performance, which significantly outperforms the current state-of-the-art, even in mismatched noise environments.en
Type of ItemPeer-Reviewed Journal Publicationen
Type of ItemΔημοσίευση σε Περιοδικό με Κριτέςel
Licensehttp://creativecommons.org/licenses/by/4.0/en
Date of Item2021-09-27-
Date of Publication2020-
SubjectVariational autoencodersen
SubjectDenoisingen
SubjectDialogue systemsen
SubjectSample-efficient statistical dialogue managersen
SubjectLeast-squares policy iterationen
Bibliographic CitationV. Diakoloukas, F. Lygerakis, M. G. Lagoudakis, and M. Kotti, “Variational denoising autoencoders and least-squares policy iteration for statistical dialogue managers,” IEEE Signal Process. Lett., vol. 27, pp. 960–964, 2020. doi: 10.1109/LSP.2020.2998361en

Services

Statistics