2 papers
math.OC2018
A Theoretical Difficulty in Approximate Dynamic Programming with Input Constraints
Xuefeng Bao, Zhi-Hong Mao, Nitin Sharma
Equipping approximate dynamic programming (ADP) with inputconstraints has a tremendous significance. This enables ADP to be applied tothe systems with actuator limitations, which i…
math.OC2018
A Supplementary Condition for the Convergence of the Control Policy during Adaptive Dynamic Programming
Xuefeng Bao, Zhi-Hong Mao, Nitin Sharma
Reinforcement learning based adaptive/approximate dynamic programming (ADP) is a powerful technique to determine an approximate optimal controller for a dynamical system. These met…