Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability

Zhao, Qingyue, Ji, Kaixuan, Zhao, Heyang, Gu, Quanquan

Open source

DOI
10.48550/arxiv.2605.09214
Published
2026
Container
Not recorded
Publisher
arXiv
Open access
yes

Credibility signals

limited evidence Score 43/100 under policy 1.0.0. This is a metadata assessment, not a judgment of the paper's conclusions.

Show all credibility signals

Cite this work

BibTeX

@article{allodium:10.48550/arxiv.2605.09214,
  title = {Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability},
  author = {Zhao, Qingyue and Ji, Kaixuan and Zhao, Heyang and Gu, Quanquan},
  year = {2026},
  doi = {10.48550/arxiv.2605.09214},
  url = {https://doi.org/10.48550/arxiv.2605.09214}
}

RIS

TY  - JOUR
TI  - Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability
AU  - Zhao, Qingyue
AU  - Ji, Kaixuan
AU  - Zhao, Heyang
AU  - Gu, Quanquan
PY  - 2026
DO  - 10.48550/arxiv.2605.09214
UR  - https://doi.org/10.48550/arxiv.2605.09214
ER  - 

APA

Qingyue, Z., Kaixuan, J., Heyang, Z., & Quanquan, G. (2026). Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability. https://doi.org/10.48550/arxiv.2605.09214

Source records