@inproceedings{coldstartreinforcementlearningwith,
  title = {Cold-Start Reinforcement Learning with Softmax Policy Gradient},
  author = {Nan Ding and Radu Soricut},
  year = {2017},
  booktitle = {NeurIPS 2017 12},
  eprint = {1709.09346},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1709.09346v2},
}