@article{vlearnoffpolicylearningwithefficient,
  title = {Vlearn: Off-Policy Learning with Efficient State-Value Function Estimation},
  author = {Fabian Otto and Philipp Becker and Ngo Anh Vien and Gerhard Neumann},
  year = {2024},
  eprint = {2403.04453},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.04453v2},
}