@article{JMLR:v17:10-245,
  author  = {Mohammad Ghavamzadeh and Yaakov Engel and Michal Valko},
  title   = {Bayesian Policy Gradient and Actor-Critic Algorithms},
  journal = {Journal of Machine Learning Research},
  year    = {2016},
  volume  = {17},
  number  = {66},
  pages   = {1--53},
  url     = {http://jmlr.org/papers/v17/10-245.html}
}