Lyapunov-Based Sample Complexity Analysis for Weakly-Coupled MDPs
cs.LG, math.OC, math.PR, stat.ML
Submitted: 2026-06-12
Updated: 2026-11-07
Terminology
Sources
- Model-Based Reinforcement Learning with a Generative Model is Minimax Optimal
- Lagrangian Index Policy for Restless Bandits with Average Reward
- Achieving Exponential Asymptotic Optimality in Average-Reward Restless Bandits without Global Attractor Assumption
- Unichain and Aperiodicity are Sufficient for Asymptotic Optimality of Average-Reward Restless Bandits
- Efficiently Solving MDPs with Stochastic Mirror Descent
- Thompson Sampling in Non-Episodic Restless Bandits
- Near-Optimal Sample Complexity for MDPs via Anchoring
- Dealing with unbounded gradients in stochastic saddle-point optimization
- Finding good policies in average-reward Markov Decision Processes without prior knowledge
- Near Sample-Optimal Reduction-based Policy Learning for Average Reward MDP
- Optimal Sample Complexity for Average Reward Markov Decision Processes
- Achieving $\tilde{\mathcal{O}}(1/N)$ Optimality Gap in Restless Bandits through Gaussian Approximation
- Projection-based Lyapunov method for fully heterogeneous weakly-coupled MDPs
- The Plug-in Approach for Average-Reward and Discounted MDPs: Optimal Sample Complexity Analysis
- Span-Agnostic Optimal Sample Complexity and Oracle Inequalities for Average-Reward RL
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