Research map / Bandits and online learning / Multi-armed bandits
Budget-Constrained Multi-Armed Bandits With Multiple Plays
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 UCB on estimated bang-per-buck ratios for arm selection | UCB-MB · Stochastic budget-constrained multiple-play bandits | expected regret upper bound: O(NK^4 \log B) | Helped |
| Extend Exp3.M to use budget-based termination and cost feedback | Exp3.M · Adversarial budget-constrained multiple-play bandits | regret upper bound: O(\sqrt{NB\log(N/K)}) | Helped |
| Add confidence bonuses to the budgeted adversarial multiple-play updates | Exp3.M.B · Adversarial budget-constrained multiple-play bandits | high-probability regret upper bound: 2\sqrt{3}\sqrt{\frac{NB(1-c_{\min})}{c_{\min}}\log\frac{N}{K}} + 4\sqrt{6}\frac{N-K}{N-1}\log\left( \frac{NB}{Kc_{\min}\ | Helped |
Closest papers by meaning
- Infinitely Many-Armed Bandits with Budget Constraints (AAAI 2017 · similarity 0.92)
- Stochastic Bandits Robust to Adversarial Attacks (ICLR 2025 · similarity 0.90)
- Multi-Armed Bandits With Best-Action Queries (NeurIPS 2026 · similarity 0.89)
- Beyond Primal-Dual Methods in Bandits with Stochastic and Adversarial Constraints (NeurIPS 2024 · similarity 0.89)
- Strategic Multi-Armed Bandit Problems Under Debt-Free Reporting (NeurIPS 2024 · similarity 0.88)
- Improved Best-of-Both-Worlds Regret for Bandits with Delayed Feedback (NeurIPS 2025 · 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.