Research map / Bandits and online learning / Multi-armed bandits
Restless-UCB, an Efficient and Low-complexity Algorithm for Online Restless 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 |
|---|---|---|---|
| Construct an optimistic offline instance from confidence bounds and commit to its policy | Restless-UCB · Real-world wireless communication datasets | regret | Helped |
| Construct an optimistic offline instance from confidence bounds and commit to its policy | Restless-UCB · Constructed two-arm instances | regret | Mixed |
| Use Restless-UCB instead of Colored-UCRL2 | Online restless bandit · Running time, 3 to 5 arms | running time: 326s vs 5s; 8892s vs 5s; 129387s vs 5s | Helped |
| Use Restless-UCB instead of TS-4 | Online restless bandit · Constructed two-arm instances | regret | Helped |
| Use an approximate offline oracle with ratio λ | Restless-UCB · Online restless bandit | approximation regret upper bound: \tilde{O}(T^{2\over 3}) | Helped |
Closest papers by meaning
- Graph-Triggered Rising Bandits (ICML 2024 · similarity 0.89)
- Provably Efficient Reinforcement Learning for Adversarial Restless Multi-Armed Bandits with Unknown Transitions and Bandit Feedback (ICML 2024 · similarity 0.89)
- Block Optimism for Nonstationary Bandits with Latent Linear Dynamics (NeurIPS 2026 · similarity 0.88)
- DOPL: Direct Online Preference Learning for Restless Bandits with Preference Feedback (ICLR 2025 · similarity 0.88)
- Adaptive Regret for Bandits Made Possible: Two Queries Suffice (ICLR 2024 · similarity 0.87)
- Achieving $\tilde{\mathcal{O}}(1/N)$ Optimality Gap in Restless Bandits through Gaussian Approximation (NeurIPS 2025 · 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.