@misc{lopez2021efficient,
  title={Efficient Off-Policy Q-Learning for Data-Based Discrete-Time LQR Problems},
  author={Victor G. Lopez and Mohammad Alsalti and Matthias A. Müller},
  year={2021},
  eprint={2105.07761},
  archivePrefix={arXiv},
  primaryClass={eess.SY},
  doi={10.1109/TAC.2023.3235967},
  url={https://arxiv.org/abs/2105.07761}
}