Research map / Bandits and online learning / Multi-armed bandits
A One-Size-Fits-All Solution to Conservative Bandit Problems
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 GenCB's sample-path safety check based on received cumulative reward instead of a lower confidence bound | Conservative bandit algorithms · CMAB, CLB, CCCB | conservative regret | Helped |
| Apply GenCB with UCB and enforce the sample-path reward constraint | CMAB · CMAB | conservative regret | Helped |
| Apply GenCB with LinUCB and enforce the sample-path reward constraint | CLB · CLB | conservative regret | Helped |
| Apply GenCB with C2UCB and enforce the sample-path reward constraint | CCCB · CCCB | conservative regret | Helped |
| Add a mean-variance constraint and use upper confidence bounds for mean-variance arm selection | MV-CUCB · MV-CBP | cumulative conservative regret | Helped |
| Enforce conservative exploration | Standard bandit algorithms · CMAB, CLB, CCCB | exploration-phase reward relative to baseline | Helped |
Closest papers by meaning
- Improved Algorithms for Conservative Exploration in Bandits (AAAI 2020 · similarity 0.92)
- Stage-wise Conservative Linear Bandits (NeurIPS 2020 · similarity 0.92)
- Conservative Contextual Bandits: Beyond Linear Representations (ICLR 2025 · similarity 0.90)
- Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals (ICML 2024 · similarity 0.88)
- Catoni Contextual Bandits are Robust to Heavy-tailed Rewards (ICML 2025 · similarity 0.88)
- Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox (NeurIPS 2024 · similarity 0.87)
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.