@article{dpokreinforcementlearningforfinetuning,
  title = {DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models},
  author = {Ying Fan and Olivia Watkins and Yuqing Du and Hao liu and MoonKyung Ryu and Craig Boutilier and Pieter Abbeel and Mohammad Ghavamzadeh and Kangwook Lee and Kimin Lee},
  year = {2023},
  eprint = {2305.16381},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2305.16381v3},
}