Research map / Bandits and online learning / Multi-armed bandits
Pure Exploration with Multiple Correct Answers
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 Sticky Track-and-Stop instead of unmodified Track-and-Stop with C-tracking | Any Half-Space, K=10 · Any Half-Space, K=10 | mean stopping time: 24K -> 16K | Helped |
| Use Sticky Track-and-Stop with confidence-based answer selection and sticking | Multiple-answer bandit problems · Multiple-answer bandit problems | asymptotic sample complexity ratio | Helped |
| Track oracle weights without sticking to a selected oracle answer | Track-and-Stop with C-tracking · Multiple-answer problems with non-convex oracle weight sets | asymptotic sample complexity | Hurt |
| Use D-tracking rather than C-tracking | Track-and-Stop · Single-answer problems with non-singleton oracle weight sets | convergence to oracle weights | Hurt |
| Use C-tracking for instances with a unique oracle answer | Track-and-Stop · Instances with a singleton set of oracle answers | asymptotic sample complexity | Helped |
Closest papers by meaning
- Preference-based Pure Exploration (NeurIPS 2024 · similarity 0.88)
- The Batch Complexity of Bandit Pure Exploration (ICML 2025 · similarity 0.88)
- Near Optimal Non-asymptotic Sample Complexity of 1-Identification (ICML 2025 · similarity 0.87)
- Greedy Algorithms for Structured Bandits: A Sharp Characterization of Asymptotic Success / Failure (NeurIPS 2025 · similarity 0.87)
- Geometry Meets Incentives: Sample-Efficient Incentivized Exploration with Linear Contexts (NeurIPS 2025 · similarity 0.86)
- Nearly Tight Bounds for Exploration in Streaming Multi-Armed Bandits with Known Optimality Gap (AAAI 2025 · similarity 0.86)
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.