AI Paper Atlas

Research map / Bandits and online learning / Multi-armed bandits

Combinatorial Rising Bandits

Seockbean Song, Youngsik Yoon, Siwei Wang, Wei Chen, Jungseul Ok

ICLR 2026 · Bandits and online learning › Multi-armed bandits · approach: Non-stationary and structured-reward bandits · 1 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 CRUCB instead of R-ed-UCB and sliding-window baselinesonline shortest path · Path-easy syntheticcumulative regretImproved
use CRUCB instead of R-ed-UCB and sliding-window baselinesonline shortest path · Path-complex syntheticcumulative regretImproved
use non-combinatorial sliding-window algorithms (SW-UCB, SW-TS) instead of combinatorial ones (SW-CUCB, SW-CTS) (ablation)sliding-window bandits · Path-easy and Path-complexcumulative regretImproved
use CRUCB instead of baselineshierarchical RL path selection · AntMaze-easycumulative regretImproved
use CRUCB instead of baselineshierarchical RL path selection · AntMaze-complexcumulative regretImproved
ignore the combinatorial structure (R-ed-UCB) in rising bandit (ablation)R-ed-UCB · toy shortest pathcumulative regretHurt

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