Achieving an O(1/N) Optimality Gap in Average-Reward Weakly-Coupled MDPs
cs.LG, math.OC, math.PR
Submitted: 2026-09-29
Updated: 2026-09-29
Sources
- Achieving Exponential Asymptotic Optimality in Average-Reward Restless Bandits without Global Attractor Assumption
- Asymptotically Optimal Policies for Weakly Coupled Markov Decision Processes
- Model Predictive Control is almost Optimal for Heterogeneous Restless Multi-armed Bandits
- Restless Bandits with Many Arms: Beating the Central Limit Theorem
- Reoptimization Nearly Solves Weakly Coupled Markov Decision Processes
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks