@misc{haarnoja2018soft,
  title={Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor},
  author={Tuomas Haarnoja and Aurick Zhou and Pieter Abbeel and Sergey Levine},
  year={2018},
  eprint={1801.01290},
  archivePrefix={arXiv},
  primaryClass={cs.LG},
  url={https://arxiv.org/abs/1801.01290}
}