@article{pathspacemirrordescentforonpolicyreinfor,
  title = {Path-Space Mirror Descent for On-Policy Reinforcement Learning under the Generalized Schrödinger Bridge},
  author = {Yuehu Gong and Zeyuan Wang and Yulin Chen and Shutong Ding and Qingyuan Zhou and Yanwei Fu},
  year = {2026},
  eprint = {2603.21621},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.21621},
}