Achieving Exponential Asymptotic Optimality in Average-Reward Restless Bandits without Global Attractor Assumption
cs.LG, math.OC, math.PR
Submitted: 2024-05-28
Updated: 2026-10-31
Terminology
Sources
- Exponential Convergence Rate for the Asymptotic Optimality of Whittle Index Policy
- Reoptimization Nearly Solves Weakly Coupled Markov Decision Processes
- An Asymptotically Optimal Index Policy for Finite-Horizon Restless Bandits
- Unichain and Aperiodicity are Sufficient for Asymptotic Optimality of Average-Reward Restless Bandits
- An Optimal-Control Approach to Infinite-Horizon Restless Bandits: Achieving Asymptotic Optimality with Minimal Assumptions
- Restless Bandits with Many Arms: Beating the Central Limit Theorem
- Near-optimality for infinite-horizon restless bandits with many arms
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis