Ιδρυματικό Αποθετήριο [SANDBOX]
Πολυτεχνείο Κρήτης
EN  |  EL

Αναζήτηση

Πλοήγηση

Ο Χώρος μου

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

Diakoloukas Vasileios, Lygerakis Fotios, Lagoudakis Michail, Kotti Margarita

Απλή Εγγραφή


URIhttp://purl.tuc.gr/dl/dias/A1FB74B4-8B64-46FA-B0AE-941918F57F06-
Αναγνωριστικόhttps://doi.org/10.1109/LSP.2020.2998361-
Αναγνωριστικόhttps://ieeexplore.ieee.org/document/9103219-
Γλώσσαen-
Μέγεθος5 pagesen
ΤίτλοςVariational denoising autoencoders and least-squares policy iteration for statistical dialogue managersen
ΔημιουργόςDiakoloukas Vasileiosen
ΔημιουργόςΔιακολουκας Βασιλeioςel
ΔημιουργόςLygerakis Fotiosen
ΔημιουργόςΛυγερακης Φωτιοςel
ΔημιουργόςLagoudakis Michailen
ΔημιουργόςΛαγουδακης Μιχαηλel
ΔημιουργόςKotti Margaritaen
ΕκδότηςInstitute of Electrical and Electronics Engineersen
ΠερίληψηThe 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
ΤύποςPeer-Reviewed Journal Publicationen
ΤύποςΔημοσίευση σε Περιοδικό με Κριτέςel
Άδεια Χρήσηςhttp://creativecommons.org/licenses/by/4.0/en
Ημερομηνία2021-09-27-
Ημερομηνία Δημοσίευσης2020-
Θεματική ΚατηγορίαVariational autoencodersen
Θεματική ΚατηγορίαDenoisingen
Θεματική ΚατηγορίαDialogue systemsen
Θεματική ΚατηγορίαSample-efficient statistical dialogue managersen
Θεματική ΚατηγορίαLeast-squares policy iterationen
Βιβλιογραφική ΑναφοράV. 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

Υπηρεσίες

Στατιστικά