Ιδρυματικό Αποθετήριο
Πολυτεχνείο Κρήτης
Πολυτεχνείο Κρήτης
EN
|
EL
| URI | http://purl.tuc.gr/dl/dias/A1FB74B4-8B64-46FA-B0AE-941918F57F06 | - |
| Αναγνωριστικό | https://doi.org/10.1109/LSP.2020.2998361 | - |
| Αναγνωριστικό | https://ieeexplore.ieee.org/document/9103219 | - |
| Γλώσσα | en | - |
| Μέγεθος | 5 pages | en |
| Τίτλος | Variational denoising autoencoders and least-squares policy iteration for statistical dialogue managers | en |
| Δημιουργός | Diakoloukas Vasileios | en |
| Δημιουργός | Διακολουκας Βασιλeioς | el |
| Δημιουργός | Lygerakis Fotios | en |
| Δημιουργός | Λυγερακης Φωτιος | el |
| Δημιουργός | Lagoudakis Michail | en |
| Δημιουργός | Λαγουδακης Μιχαηλ | el |
| Δημιουργός | Kotti Margarita | en |
| Εκδότης | Institute of Electrical and Electronics Engineers | en |
| Περίληψη | The 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 |
| Τύπος | Peer-Reviewed Journal Publication | en |
| Τύπος | Δημοσίευση σε Περιοδικό με Κριτές | el |
| Άδεια Χρήσης | http://creativecommons.org/licenses/by/4.0/ | en |
| Ημερομηνία | 2021-09-27 | - |
| Ημερομηνία Δημοσίευσης | 2020 | - |
| Θεματική Κατηγορία | Variational autoencoders | en |
| Θεματική Κατηγορία | Denoising | en |
| Θεματική Κατηγορία | Dialogue systems | en |
| Θεματική Κατηγορία | Sample-efficient statistical dialogue managers | en |
| Θεματική Κατηγορία | Least-squares policy iteration | en |
| Βιβλιογραφική Αναφορά | V. 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.2020.2998361 | en |
Copyright © DIAS 2013
