@article{learninginstructuredmdpswithconvexcost,
  title = {Learning in structured MDPs with convex cost functions: Improved regret bounds for inventory management},
  author = {Shipra Agrawal and Randy Jia},
  year = {2019},
  eprint = {1905.04337},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1905.04337v1},
}