@article{learningadiffusionmodelpolicyfrom,
  title = {Learning a Diffusion Model Policy from Rewards via Q-Score Matching},
  author = {Michael Psenka and Alejandro Escontrela and Pieter Abbeel and Yi Ma},
  year = {2023},
  eprint = {2312.11752},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2312.11752v4},
}