Research map / Bandits and online learning / Online convex optimization and games
Regret of Queueing 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 |
|---|---|---|---|
| Add structured exploration (explore with prob. min{1, 3K log^2 t / t}) to Thompson sampling (Q-ThS) | Thompson sampling for queueing bandit · Queueing bandit simulations (K=5, eps=0.1) | queue-regret Psi(t) | Mixed |
| Decrease load gap eps (heavier traffic) with Q-ThS (ablation) | Q-ThS · Simulation K=5 with eps in {0.05,0.1,0.15} | queue-regret Psi(t) | Hurt |
| Increase number of servers K from 5 to 7 (ablation) | Q-ThS · Simulation eps in {0.05,0.1,0.15} | queue-regret Psi(t) | Hurt |
| Late-stage regret of Q-ThS vs. alpha-consistent lower bound | Q-ThS · Theory: late stage | queue-regret scaling | Helped |
Closest papers by meaning
- Queueing Matching Bandits with Preference Feedback (NeurIPS 2024 · similarity 0.92)
- Algorithm for Contextual Queueing Bandits with Rate-Optimal Queue Length Regret (NeurIPS 2026 · similarity 0.91)
- Delay as Payoff in MAB (AAAI 2025 · similarity 0.88)
- Reinforcement Learning and Regret Bounds for Admission Control (ICML 2024 · similarity 0.86)
- Near-Optimal Regret-Queue Length Tradeoff in Online Learning for Two-Sided Markets (NeurIPS 2025 · similarity 0.86)
- Oracle-Efficient Combinatorial Semi-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.