Non-stationary Bandits and Meta-Learning with a Small Set of Optimal Arms. Azizi, J., Duong, T., Abbasi-Yadkori, Y., György, A., Vernade, C., & Ghavamzadeh, M. Reinforcement Learning Journal, 5:2461–2491, 2024.
bibtex   
@article{azizi2024stationary,
    title={Non-stationary Bandits and Meta-Learning with a Small Set of Optimal Arms},
    author={Azizi, Javad and Duong, Thang and Abbasi-Yadkori, Yasin and Gy{\"{o}}rgy, Andr{\'{a}}s and Vernade, Claire and Ghavamzadeh, Mohammad},
    journal={Reinforcement Learning Journal},
    volume={5},
    pages={2461--2491},
    year={2024}
}

Downloads: 0