Pegah Alizadeh, Yann Chevaleyre, François Lévy. Advantage based value iteration for Markov decision processes with unknown rewards. In 2016 International Joint Conference on Neural Networks, IJCNN 2016, Vancouver, BC, Canada, July 24-29, 2016. pages 3837-3844, IEEE, 2016. [doi]
@inproceedings{AlizadehCL16-0,
title = {Advantage based value iteration for Markov decision processes with unknown rewards},
author = {Pegah Alizadeh and Yann Chevaleyre and François Lévy},
year = {2016},
doi = {10.1109/IJCNN.2016.7727695},
url = {http://dx.doi.org/10.1109/IJCNN.2016.7727695},
researchr = {https://researchr.org/publication/AlizadehCL16-0},
cites = {0},
citedby = {0},
pages = {3837-3844},
booktitle = {2016 International Joint Conference on Neural Networks, IJCNN 2016, Vancouver, BC, Canada, July 24-29, 2016},
publisher = {IEEE},
isbn = {978-1-5090-0620-5},
}