Lucie Daubigney, Matthieu Geist, Olivier Pietquin. Off-policy learning in large-scale POMDP-based dialogue systems. In 2012 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2012, Kyoto, Japan, March 25-30, 2012. pages 4989-4992, IEEE, 2012. [doi]
@inproceedings{DaubigneyGP12, title = {Off-policy learning in large-scale POMDP-based dialogue systems}, author = {Lucie Daubigney and Matthieu Geist and Olivier Pietquin}, year = {2012}, doi = {10.1109/ICASSP.2012.6289040}, url = {http://dx.doi.org/10.1109/ICASSP.2012.6289040}, researchr = {https://researchr.org/publication/DaubigneyGP12}, cites = {0}, citedby = {0}, pages = {4989-4992}, booktitle = {2012 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2012, Kyoto, Japan, March 25-30, 2012}, publisher = {IEEE}, isbn = {978-1-4673-0046-9}, }