@article{humaninthelooppolicyoptimizationfor,
  title = {Human-in-the-Loop Policy Optimization for Preference-Based Multi-Objective Reinforcement Learning},
  author = {Ke Li and Han Guo},
  year = {2024},
  eprint = {2401.02160},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2401.02160v1},
}