@article{reinforcementlearningviavaluegradientflo,
  title = {Reinforcement Learning via Value Gradient Flow},
  author = {Haoran Xu and Kaiwen Hu and Somayeh Sojoudi and Amy Zhang},
  year = {2026},
  eprint = {2604.14265},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.14265},
}