AI Paper Atlas

Research map / Bandits and online learning / Contextual bandits and Thompson sampling

Bi-Level Contextual Bandits for Individualized Resource Allocation Under Delayed Feedback

Mohammadsina Almasi, Hadis Anahideh

AAAI 2026 · Bandits and online learning › Contextual bandits and Thompson sampling · approach: Practical contextual bandit extensions · 2 citations (OpenAlex)

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 bi-level MetaCUB instead of UCB for allocationMetaCUB · ELS Black, delayedsubgroup allocation ratio: 0.33 -> 1.00Improved
use MetaCUB instead of EXP3MetaCUB · ELS Asian, delayedsubgroup allocation ratio: 0.27 -> 1.02Improved
use MetaCUB instead of UCBMetaCUB · ELS White, delayedsubgroup allocation ratio: 1.42 -> 0.96Improved
use MetaCUB instead of UCBMetaCUB · JOBS Black, delayedsubgroup allocation ratio: 0.54 -> 0.98Improved
use MetaCUB instead of DUCBMetaCUB · JOBS Black, delayedsubgroup allocation ratio: 1.29 -> 0.98Improved
use MetaCUB instead of SWUCBMetaCUB · JOBS Black, delayedsubgroup allocation ratio: 1.30 -> 0.98Improved
use MetaCUB instead of EXP3MetaCUB · JOBS Black, immediatesubgroup allocation ratio: 1.20 -> 1.03Improved
use MetaCUB instead of UCBMetaCUB · ELS Asian, immediatesubgroup allocation ratio: 0.62 -> 0.84Improved
use MetaCUB instead of baselinesMetaCUB · ELS and JOBS cumulative regretcumulative regretImproved
use nonlinear (neural) reward model instead of linearall algorithms · ELS and JOBS cumulative regretcumulative regretImproved
use Type-I (peaked) instead of Type-II (flat) delay kernelsall algorithms · ELS and JOBS cumulative regretcumulative regretImproved
add delay-aware kernel modeling and subgroup structureMetaCUB · delayed feedback regretcumulative regretImproved

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