Ιδρυματικό Αποθετήριο
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

Πλήρης Εγγραφή


URI: http://purl.tuc.gr/dl/dias/A1FB74B4-8B64-46FA-B0AE-941918F57F06
Έτος 2020
Τύπος Δημοσίευση σε Περιοδικό με Κριτές
Άδεια Χρήσης
Λεπτομέρειες
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 https://doi.org/10.1109/LSP.2020.2998361
Εμφανίζεται στις Συλλογές

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.

Υπηρεσίες

Στατιστικά