@article{reinforcementlearningwithdynamicboltzman,
  title = {Reinforcement Learning with Dynamic Boltzmann Softmax Updates},
  author = {Ling Pan and Qingpeng Cai and Qi Meng and Wei Chen and Longbo Huang and Tie-Yan Liu},
  year = {2019},
  eprint = {1903.05926},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1903.05926v4},
}