@article{posteriorsamplingforreinforcementlearnin,
  title = {Posterior Sampling for Reinforcement Learning Without Episodes},
  author = {Ian Osband and Benjamin Van Roy},
  year = {2016},
  eprint = {1608.02731},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1608.02731v1},
}