@article{instancedependentregretboundsforlearning,
  title = {Instance-Dependent Regret Bounds for Learning Two-Player Zero-Sum Games with Bandit Feedback},
  author = {Shinji Ito and Haipeng Luo and Taira Tsuchiya and Yue Wu},
  year = {2025},
  eprint = {2502.17625},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.17625v1},
}