@article{guidedflowpolicylearningfromhighvalueact,
  title = {Guided Flow Policy: Learning from High-Value Actions in Offline Reinforcement Learning},
  author = {Franki Nguimatsia Tiofack and Théotime Le Hellard and Fabian Schramm and Nicolas Perrin-Gilbert and Justin Carpentier},
  year = {2025},
  eprint = {2512.03973},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2512.03973},
}