Research map / Bandits and online learning / Multi-armed bandits
Optimistic Whittle Index Policy: Online Learning for 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 direct Whittle-index maximization rather than future-value maximization (ablation) | UCWhittle · 500 timesteps, N=30 arms, budget B=6 | runtime: 6.1× speedup | Helped |
| Use direct Whittle-index maximization rather than future-value maximization (ablation) | UCWhittle · Three domains | regret | No clear effect |
| Use optimistic Whittle indices from confidence-bounded transition estimates | UCWhittle · Three domains | regret | Helped |
| Use UCWhittle-value instead of the regret baselines | UCWhittle-value · Low-budget settings | regret | Helped |
| Use ExtremeWhittle instead of a random policy | ExtremeWhittle · Three domains, early episodes | regret | Hurt |
| Use WIQL instead of a random policy | WIQL · Evaluated time horizons across three domains | regret | No clear effect |
Closest papers by meaning
- Global Rewards in Restless Multi-Armed Bandits (NeurIPS 2024 · similarity 0.90)
- DOPL: Direct Online Preference Learning for Restless Bandits with Preference Feedback (ICLR 2025 · similarity 0.89)
- Provably Efficient Reinforcement Learning for Adversarial Restless Multi-Armed Bandits with Unknown Transitions and Bandit Feedback (ICML 2024 · similarity 0.89)
- Online Restless Multi-Armed Bandits with Long-Term Fairness Constraints (AAAI 2024 · similarity 0.88)
- Block Optimism for Nonstationary Bandits with Latent Linear Dynamics (NeurIPS 2026 · similarity 0.88)
- The Bandit Whisperer: Communication Learning for Restless Bandits (AAAI 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.