@misc{W2781726626,
  author = {Tuomas Haarnoja and Aurick Zhou and Pieter Abbeel and Sergey Levine},
  title = {Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor},
  year = {2018},
  howpublished = {arXiv (Cornell University)},
  doi = {https://doi.org/10.48550/arxiv.1801.01290}
}