Research map / Bandits and online learning / Multi-armed bandits
PAC Identification of Many Good Arms in Stochastic Multi-Armed Bandits
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 GLUCB instead of F2 for selecting one arm from the best m | Q-F on the five Bernoulli instances · I_n, n = 10, 20, 50, 100, 200 | number of samples | Helped |
| Select k arms from the best m rather than requiring the best k-arm subset | GLUCB · I_20, m = 10, k < m | number of samples | Helped |
| Increase the number of arms | F2 and GLUCB · Q-F, m = 0.1 × n | number of samples | Hurt |
| Increase m while keeping k = 1 | F2 and GLUCB · Q-F on I_10, m varied from 1 to 5 | number of samples | Helped |
| Use GLUCB rather than F2 when m is larger and k = 1 | Q-F on I_10 · Q-F, m varied from 1 to 5 | fraction of samples allocated to the best arm | Helped |
Closest papers by meaning
- Adaptive Multiple-Arm Identification (ICML 2017 · similarity 0.94)
- PAC Identification of a Bandit Arm Relative to a Reward Quantile (AAAI 2017 · similarity 0.93)
- PAC Lower Bounds and Efficient Algorithms for The Max K-Armed Bandit Problem (ICML 2016 · similarity 0.93)
- Near Optimal Best Arm Identification for Clustered Bandits (ICML 2025 · similarity 0.91)
- On Universally Optimal Algorithms for A/B Testing (ICML 2024 · similarity 0.90)
- Almost Minimax Optimal Best Arm Identification in Piecewise Stationary Linear Bandits (NeurIPS 2024 · similarity 0.90)
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.