Research map / Bandits and online learning / Multi-armed bandits
Blocking 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 |
|---|---|---|---|
| increase K* (number of arms played linearly often via free exploration, via larger identical delay) | UCB Greedy · Synthetic blocking bandits, identical delays | regret vs oracle greedy | Helped |
| larger K* in blocking constraints | UCB Greedy · Jester jokes recommendation | regret | Helped |
| K* equals Kg (all played arms freely explored) | UCB Greedy · Synthetic blocking bandits | regret scaling in T | Helped |
| UCB Greedy instead of oracle greedy when oracle greedy is suboptimal | blocking bandit instances · Synthetic blocking bandits (Fig. 1c) | cumulative regret vs oracle greedy | Helped |
Closest papers by meaning
- Combinatorial Blocking Bandits with Stochastic Delays (ICML 2021 · similarity 0.93)
- Regret Minimisation in Multi-Armed Bandits Using Bounded Arm Memory (AAAI 2020 · similarity 0.91)
- Greedy Algorithms for Structured Bandits: A Sharp Characterization of Asymptotic Success / Failure (NeurIPS 2025 · similarity 0.89)
- Strategic Multi-Armed Bandit Problems Under Debt-Free Reporting (NeurIPS 2024 · similarity 0.89)
- On Multi-Armed Bandit with Impatient Arms (ICML 2024 · similarity 0.89)
- Combinatorial Stochastic-Greedy Bandit (AAAI 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.