Research map / Bandits and online learning / Multi-armed bandits
Combinatorial Blocking Bandits with Stochastic Delays
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 the greedy heuristic with an (α, β)-approximation oracle | CBBSD full-information · CBBSD full-information | approximation ratio: \frac{\alpha\beta}{1 + \alpha\beta} | Helped |
| Use UCB indices in the greedy heuristic | CBBSD-UCB · CBBSD bandit | approximate regret: \frac{48}{1 + \alpha\beta}\sum_{i\in \A}\frac{r\cdot \ln{T}}{\Delta_{\min}^i} | Helped |
| Use UCB indices in the greedy heuristic | CBBSD-UCB · CBBSD bandit | approximate regret: \frac{14\sqrt{k\cdot r\cdot T\ln{T}}}{1 + \alpha \beta} | Helped |
| Require feasible sets to satisfy the hereditary property | CBBSD · CBBSD computational tractability | approximation guarantee: 1 - \frac{1}{e} + \epsilon; \Omega(k^{-\frac{1}{2} + \epsilon}) | Mixed |
| Compare against an optimal algorithm that knows delay realizations | CBBSD · CBBSD with known delay realizations for the comparator | approximation ratio: \omega(\frac{1}{d_{\max}}) | Hurt |
Closest papers by meaning
- Blocking Bandits (NeurIPS 2019 · similarity 0.93)
- Stochastic bandits with arm-dependent delays (ICML 2020 · similarity 0.91)
- Combinatorial Stochastic-Greedy Bandit (AAAI 2024 · similarity 0.91)
- Near-Optimal Stochastic Linear Bandits with Delay (NeurIPS 2026 · similarity 0.89)
- Delay as Payoff in MAB (AAAI 2025 · similarity 0.89)
- Optimal and Efficient Contextual Combinatorial Semi-bandits with General Function Approximation (NeurIPS 2026 · 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.