Research map / Bandits and online learning / Multi-armed bandits
Top Two Algorithms Revisited
Marc Jourdan, Rémy Degenne, Dorian Baudry, Rianne de Heide, Emilie Kaufmann
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use EB leader with TCI challenger instead of TC (ablation) | beta-EB-TC · Bernoulli random instances K=10 | empirical stopping time | Improved |
| Top Two variants (EB-TCI, TS-TC, TS-TCI) vs Kinf-DKM | Top Two sampling rules · DSSAT crop management | empirical stopping time | Improved |
| Kinf-LUCB instead of uniform sampling | LUCB baseline · DSSAT crop management | empirical stopping time | Hurt |
| KL-LUCB instead of Top Two on Bernoulli instances | baseline · Bernoulli random instances K=10 | empirical stopping time | Hurt |
| uniform sampling vs KL-LUCB on symmetric instance | uniform sampling · Bernoulli mu=(0.5,0.45,0.45) | empirical stopping time | Improved |
| use EB-TC (fully deterministic) with more runs | beta-EB-TC · Bernoulli instances | robustness of stopping time | Hurt |
Closest papers by meaning
- Optimal Multi-Fidelity Best-Arm Identification (NeurIPS 2024 · similarity 0.90)
- Balancing Performance and Costs in Best Arm Identification (NeurIPS 2025 · similarity 0.90)
- Optimal Top-Two Method for Best Arm Identification and Fluid Analysis (NeurIPS 2024 · similarity 0.90)
- Sharp Non-Asymptotic Analysis of the Penalized Challenger in $\beta$-EB-TCI for Bernoulli Bandits (NeurIPS 2026 · similarity 0.89)
- On Universally Optimal Algorithms for A/B Testing (ICML 2024 · similarity 0.89)
- Fixed Confidence Best Arm Identification in the Bayesian Setting (NeurIPS 2024 · similarity 0.89)
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.
