AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

Towards a Sharp Analysis of Learning Offline $f$-Divergence-Regularized Contextual Bandits

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

ICLR 2026 · Reinforcement learning › MDPs and planning · approach: Function approximation in RL theory

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use reverse-KL regularization with less-covered reference policy (larger concentrability)KL-PCB · linear bandit (d=20, 100 arms)sub-optimality gapHurt
use chi-square regularization (strongly convex f) with varying coveragef-CB · linear bandit (d=20, 100 arms)sub-optimality gapNo clear effect
use spiky instead of uniform reference policy under KL regularizationKL-PCB · MNIST contextual banditsub-optimality gapHurt
use spiky instead of uniform reference policy under chi-square regularizationf-CB · MNIST contextual banditsub-optimality gapNo clear effect
scale strong convexity modulus alpha as 2^15/nf-CB · two-armed banditsub-optimalityNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy