Mohammad Ghavamzadeh, Yaakov Engel, Michal Valko. Bayesian Policy Gradient and Actor-Critic Algorithms. Journal of Machine Learning Research, 17, 2016. [doi]
@article{GhavamzadehEV16,
title = {Bayesian Policy Gradient and Actor-Critic Algorithms},
author = {Mohammad Ghavamzadeh and Yaakov Engel and Michal Valko},
year = {2016},
url = {http://jmlr.org/papers/v17/10-245.html},
researchr = {https://researchr.org/publication/GhavamzadehEV16},
cites = {0},
citedby = {0},
journal = {Journal of Machine Learning Research},
volume = {17},
}