@article{addressingvalueestimationerrorsin,
  title = {Distributional Soft Actor-Critic: Off-Policy Reinforcement Learning for Addressing Value Estimation Errors},
  author = {Jingliang Duan and Yang Guan and Shengbo Eben Li and Yangang Ren and Bo Cheng},
  year = {2020},
  eprint = {2001.02811},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2001.02811v3},
}