@inproceedings{optimisticposteriorsamplingfor,
  title = {Optimistic posterior sampling for reinforcement learning: worst-case regret bounds},
  author = {Shipra Agrawal and Randy Jia},
  year = {2017},
  booktitle = {NeurIPS 2017 12},
  url = {http://papers.nips.cc/paper/6718-optimistic-posterior-sampling-for-reinforcement-learning-worst-case-regret-bounds},
}