Two-stage population based training method for deep reinforcement learning

Yinda Zhou, Weiming Liu 0004, Bin Li 0025. Two-stage population based training method for deep reinforcement learning. In Steven Guan, editor, Proceedings of the 3rd International Conference on High Performance Compilation, Computing and Communications, HP3C 2019, Xi'an, China, March 08-10, 2019. pages 38-44, ACM, 2019. [doi]

@inproceedings{Zhou0019-0,
  title = {Two-stage population based training method for deep reinforcement learning},
  author = {Yinda Zhou and Weiming Liu 0004 and Bin Li 0025},
  year = {2019},
  doi = {10.1145/3318265.3318294},
  url = {https://doi.org/10.1145/3318265.3318294},
  researchr = {https://researchr.org/publication/Zhou0019-0},
  cites = {0},
  citedby = {0},
  pages = {38-44},
  booktitle = {Proceedings of the 3rd International Conference on High Performance Compilation, Computing and Communications, HP3C 2019, Xi'an, China, March 08-10, 2019},
  editor = {Steven Guan},
  publisher = {ACM},
  isbn = {978-1-4503-6638-0},
}