@article{thompsonsamplingforcontextualbanditswith,
  title = {Thompson Sampling for Contextual Bandits with Linear Payoffs},
  author = {Shipra Agrawal and Navin Goyal},
  year = {2012},
  eprint = {1209.3352},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1209.3352v4},
}