Research map / Bandits and online learning / Multi-armed bandits
Anytime Exploration for Multi-armed Bandits using Confidence Information
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 AT-LUCB instead of Uniform and DSAR | AT-LUCB · Linear and Polynomial, n=1000, m=10 and 50 | smallest mean and sum of means of recommended set | Helped |
| Use AT-LUCB instead of DSAR on Polynomial in the late stage | AT-LUCB · Polynomial, top-m | sum of means | Hurt |
| Recommend empirical top-m from end of previous stage (DSAR-Naive) instead of current empirical top-m (ablation) | DSAR · Toy instances | stability and quality | Mixed |
| Recommend most pulled arm with ties broken by empirical mean in DSAR (ablation) | DSAR · Toy instances | overall performance | Hurt |
| Use AT-LUCB instead of Uniform, UCB, DSH, DSAR on Sparse and Linear | AT-LUCB · Anytime Explore-1, Sparse and Linear | misidentification probability and mean of recommended arm | Helped |
| Use AT-LUCB instead of DSAR and DSH on Polynomial | AT-LUCB · Anytime Explore-1, Polynomial | misidentification probability: 6.99 | Hurt |
| Use AT-LUCB instead of DSAR on cartoon caption data | AT-LUCB · New Yorker caption contest, n=496, m=50 | smallest mean | Helped |
| Use AT-LUCB instead of DSAR on cartoon caption data | AT-LUCB · New Yorker caption contest, n=496, m=50 | sum of means | No clear effect |
| Use AT-LUCB instead of lil' UCB | AT-LUCB · New Yorker caption contest | smallest mean | Helped |
Closest papers by meaning
- Anytime optimal algorithms in stochastic multi-armed bandits (ICML 2016 · similarity 0.91)
- A Closer Look at the Worst-case Behavior of Multi-armed Bandit Algorithms (NeurIPS 2021 · similarity 0.91)
- The Batch Complexity of Bandit Pure Exploration (ICML 2025 · similarity 0.90)
- Forced Exploration in Bandit Problems (AAAI 2024 · similarity 0.89)
- Infrequent Exploration in Linear Bandits (NeurIPS 2025 · similarity 0.88)
- On Multi-Armed Bandit with Impatient Arms (ICML 2024 · similarity 0.88)
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.