Convergence and Stability of Optimal Regulation via Generalized N -Step Value Gradient Learning.
Sign Up to like & getrecommendations! Published in 2023 at "IEEE transactions on neural networks and learning systems"
DOI: 10.1109/tnnls.2023.3245630
Abstract: In this article, the generalized N -step value gradient learning (GNSVGL) algorithm, which takes a long-term prediction parameter λ into account, is developed for infinite horizon discounted near-optimal control of discrete-time nonlinear systems. The proposed… read more here.
Keywords: step value; gradient learning; value gradient; value ... See more keywords