@article{switchbasedactivedeepdynaqefficient,
  title = {Switch-based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy Learning},
  author = {Yuexin Wu and Xiujun Li and Jingjing Liu and Jianfeng Gao and Yiming Yang},
  year = {2018},
  eprint = {1811.07550},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1811.07550v1},
}