@article{learningpolicyfromasingletrajectoryinave,
  title = {Learning Policy from a Single Trajectory in Average-Reward Markov Decision Process},
  author = {Jongmin Lee and Ernest K. Ryu and Vaneet Aggarwal},
  year = {2026},
  eprint = {2606.16729},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.16729},
}