Research map / Bandits and online learning / Multi-armed bandits
Non-Asymptotic Pure Exploration by Solving Games
Rémy Degenne, Wouter M. Koolen, Pierre Ménard
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 direct rather than cumulative tracking (ablation) | tracking-based sampling rules · Best Arm and Minimum Threshold experiments | sample complexity | Improved |
| use uniform sampling instead of an adaptive sampling rule (ablation) | pure exploration algorithms · Best Arm and Minimum Threshold experiments | sample complexity | Hurt |
| follow the oracle proportions (ablation) | pure exploration sampling · Best Arm experiments | sample complexity | Hurt |
| use Track-and-Stop rather than Optimistic Track-and-Stop (ablation) | pure exploration sampling · sparse-allocation experiment | sample complexity | Hurt |
| use Optimistic Track-and-Stop | pure exploration sampling · sparse-allocation experiment at δ=10^-20 | sample complexity | Improved |
| use the simplified single learner instead of partitioning rounds by the candidate answer (ablation) | AdaHedge vs Best-Response (D) · Best Arm and Minimum Threshold experiments | sample complexity | No clear effect |
Closest papers by meaning
- Fast Pure Exploration via Frank-Wolfe (NeurIPS 2021 · similarity 0.91)
- Near Optimal Non-asymptotic Sample Complexity of 1-Identification (ICML 2025 · similarity 0.89)
- The Batch Complexity of Bandit Pure Exploration (ICML 2025 · similarity 0.88)
- FraPPE: Fast and Efficient Preference-Based Pure Exploration (NeurIPS 2025 · similarity 0.87)
- Thompson Sampling for Real-Valued Combinatorial Pure Exploration of Multi-Armed Bandit (AAAI 2024 · similarity 0.86)
- Infrequent Exploration in Linear Bandits (NeurIPS 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.
