#machine learning
May 2025
Adaptive Resolving Methods for Markov Decision Processes with Function Approximations
This work considers the MDP problems with function approximation with function approximation and develops a new algorithm to solve it efficiently, based on a linear programming (LP) reformulation and repeatedly resolves the identified reduced linear system as new transition samples arrive.
Jia-Shuo Jiang, Yinyu Ye, Yiming Zong
· Operations Research Letters · 0 citations