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
Gradient Learning under Tilted Empirical Risk Minimization
Sign Up to like & getrecommendations! Published in 2022 at "Entropy"
DOI: 10.3390/e24070956
Abstract: Gradient Learning (GL), aiming to estimate the gradient of target function, has attracted much attention in variable selection problems due to its mild structure requirements and wide applicability. Despite rapid progress, the majority of the… read more here.
Keywords: risk minimization; empirical risk; gradient learning; gradient ... See more keywords