Research map / Bandits and online learning / RL theory and MDPs
Learning Infinite-Horizon Average-Reward Restless Multi-Action Bandits via Index Awareness
GUOJUN XIONG, Shufan Wang, Jian Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 UC-R2MAB (online learning) instead of GM-R2MAB (generative model) | index-aware RL · synthetic two-action and 10-action | cumulative regret | Improved |
| use GM-R2MAB instead of MAIQL at large horizon | index-aware RL · synthetic, T = 60,000 | cumulative regret | Improved |
| use GM-R2MAB instead of TS for running time | index-aware RL · synthetic two-action | running time (s): 359s -> 86s | Improved |
| use UC-R2MAB instead of MAIQL for running time | index-aware RL · synthetic two-action | running time (s): 348s -> 308s | Improved |
| use UC-R2MAB instead of TS for running time | index-aware RL · synthetic 10-action | running time (s): 681s -> 607s | Improved |
| use ERC index policy instead of Whittle, Priority, Lagrangian | index policy · synthetic two-action | optimality gap | Improved |
| use ERC index policy instead of Priority, Lagrangian | index policy · synthetic 10-action | optimality gap | Improved |
| use UC-R2MAB instead of all baselines | UC-R2MAB · wireless scheduling | regret | Improved |
| use UC-R2MAB instead of all baselines | UC-R2MAB · tuberculosis care in India | regret | Improved |
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)
- Reinforcement learning with combinatorial actions for coupled restless bandits (ICLR 2025 · similarity 0.89)
- DOPL: Direct Online Preference Learning for Restless Bandits with Preference Feedback (ICLR 2025 · similarity 0.89)
- Online Restless Multi-Armed Bandits with Long-Term Fairness Constraints (AAAI 2024 · similarity 0.88)
- The Bandit Whisperer: Communication Learning for Restless Bandits (AAAI 2025 · similarity 0.88)
- Global Rewards in Restless Multi-Armed Bandits (NeurIPS 2024 · 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.
