@article{nonlinearmultiobjectivereinforcement,
  title = {Multi-objective Reinforcement Learning with Nonlinear Preferences: Provable Approximation for Maximizing Expected Scalarized Return},
  author = {Nianli Peng and Muhang Tian and Brandon Fain},
  year = {2023},
  eprint = {2311.02544},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2311.02544v3},
}