@article{valuemirrordescentforreinforcementlearni,
  title = {Value Mirror Descent for Reinforcement Learning},
  author = {Zhichao Jia and Guanghui Lan},
  year = {2026},
  eprint = {2604.06039},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.06039},
}