Research map / Bandits and online learning / RL theory and MDPs
Reinforcement Learning Augmented Asymptotically Optimal Index Policy for Finite-Horizon 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 |
|---|---|---|---|
| Use OMR Index Policy instead of Fluid-priority policy | Finite-horizon restless bandits · Birth-and-death process simulation | accumulated reward | Helped |
| Use OMR Index Policy instead of Whittle index policy | Finite-horizon restless bandits · Birth-and-death process simulation | accumulated reward | Helped |
| Use OMR Index Policy instead of Fluid-priority policy | Finite-horizon restless bandits · Birth-and-death process simulation | average optimality gap | Helped |
| Use OMR Index Policy instead of Whittle index policy | Finite-horizon restless bandits · Birth-and-death process simulation | average optimality gap | Helped |
| Use R(MA)2B-UCB instead of Restless-UCB | Finite-horizon restless bandits · Binary-action simulation | accumulated regret | Helped |
| Use R(MA)2B-UCB instead of Thompson sampling | Finite-horizon restless bandits · Binary-action simulation | accumulated regret | Helped |
| Use R(MA)2B-UCB instead of Restless-UCB | Finite-horizon restless bandits · Binary-action simulation | running time | Helped |
| Use R(MA)2B-UCB instead of Thompson sampling | Finite-horizon restless bandits · Binary-action simulation | running time | Helped |
Closest papers by meaning
- Provably Efficient Reinforcement Learning for Adversarial Restless Multi-Armed Bandits with Unknown Transitions and Bandit Feedback (ICML 2024 · similarity 0.90)
- Achieving $\tilde{\mathcal{O}}(1/N)$ Optimality Gap in Restless Bandits through Gaussian Approximation (NeurIPS 2025 · similarity 0.89)
- Reinforcement learning with combinatorial actions for coupled restless bandits (ICLR 2025 · similarity 0.88)
- DOPL: Direct Online Preference Learning for Restless Bandits with Preference Feedback (ICLR 2025 · similarity 0.88)
- The Bandit Whisperer: Communication Learning for Restless Bandits (AAAI 2025 · similarity 0.88)
- Block Optimism for Nonstationary Bandits with Latent Linear Dynamics (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.