Research map / Bandits and online learning / Multi-armed bandits
Fairness and Welfare Quantification for Regret in 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 |
|---|---|---|---|
| Replace fixed-length initial uniform exploration with reward-triggered adaptive exploration, and use the modified NCB rule (ablation) | NCB for known-horizon stochastic MAB · Stochastic MAB, known horizon T | Nash regret: O \left( \sqrt{ \frac{k\log k \ \log T}{T} } \right) -> O \left( \sqrt{ \frac{k \log T}{T} } \right) | Helped |
| Use the doubling-trick wrapper with Modified NCB for unknown horizons | Modified NCB · Stochastic MAB, unknown horizon T | Nash regret: O \left( \sqrt{ \frac{k \log T}{T} } \right) -> O \left( \sqrt{ \frac{k \log T}{T} } \log T\right) | Mixed |
| Use standard UCB rather than the Nash confidence-bound approach | Stochastic MAB · Two-arm Bernoulli MAB counterexample | Nash regret: close to 1 | Hurt |
Closest papers by meaning
- Nash Social Welfare for Multi Armed Bandits: Trajectory-wise Expected and High Probability Regret (NeurIPS 2026 · similarity 0.95)
- Nash Regret Guarantees for Linear Bandits (NeurIPS 2023 · similarity 0.95)
- p-Mean Regret for Stochastic Bandits (AAAI 2025 · similarity 0.93)
- No-Regret Learning for Fair Multi-Agent Social Welfare Optimization (NeurIPS 2024 · similarity 0.91)
- Improved Regret Bounds for Online Fair Division with Bandit Learning (AAAI 2025 · similarity 0.89)
- Honor Among Bandits: No-Regret Learning for Online Fair Division (NeurIPS 2024 · similarity 0.89)
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.