@article{varpreinforcementlearningfromvision,
  title = {VARP: Reinforcement Learning from Vision-Language Model Feedback with Agent Regularized Preferences},
  author = {Anukriti Singh and Amisha Bhaskar and Peihong Yu and Souradip Chakraborty and Ruthwik Dasyam and Amrit Bedi and Pratap Tokekar},
  year = {2025},
  eprint = {2503.13817},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.13817v1},
}