AI Paper Atlas

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

Top Two Algorithms Revisited

Marc Jourdan, Rémy Degenne, Dorian Baudry, Rianne de Heide, Emilie Kaufmann

NeurIPS 2022 · Bandits and online learning › Multi-armed bandits · approach: Fixed-confidence versus fixed-budget identification · 3 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 EB leader with TCI challenger instead of TC (ablation)beta-EB-TC · Bernoulli random instances K=10empirical stopping timeImproved
Top Two variants (EB-TCI, TS-TC, TS-TCI) vs Kinf-DKMTop Two sampling rules · DSSAT crop managementempirical stopping timeImproved
Kinf-LUCB instead of uniform samplingLUCB baseline · DSSAT crop managementempirical stopping timeHurt
KL-LUCB instead of Top Two on Bernoulli instancesbaseline · Bernoulli random instances K=10empirical stopping timeHurt
uniform sampling vs KL-LUCB on symmetric instanceuniform sampling · Bernoulli mu=(0.5,0.45,0.45)empirical stopping timeImproved
use EB-TC (fully deterministic) with more runsbeta-EB-TC · Bernoulli instancesrobustness of stopping timeHurt

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