Kernel Metrics and Learning for Borel MDPs: Identifiability and Adaptive Control
math.OC, math.PR
Submitted: 2025-03-14
Updated: 2026-11-06
Terminology
Sources
- Thompson Sampling for Infinite-Horizon Discounted Decision Processes
- The Plug-in Approach for Average-Reward and Discounted MDPs: Optimal Sample Complexity Analysis
- Robustness to Model Approximation, Model Learning From Data, and Sample Complexity in Wasserstein Regular MDPs
Related papers
- An Accelerated Proximal Gradient Method for Bures-Wasserstein Space
- FOMTools: Development and AI-Assisted Code Generation for First-Order Methods
- Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise
- Dynamic Service Recommendation with Congestion-Dependent Joining: Near-Optimal and Constant-Factor Approximation Algorithms
- Integrating Learning and Optimization for Open Transport Capacity Pooling under Disruption
- Zeroth-Order Gradient Estimators under Decision-Dependent Noise