@article{onlineklregularizedreinforcementlearning,
  title = {Online KL-Regularized Reinforcement Learning with Function Approximation under Misspecification},
  author = {Haoyang Hong and Zichen Wang and Quanquan Gu and Huazheng Wang},
  year = {2026},
  eprint = {2606.06053},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.06053},
}