Accelerated stochastic learning control via adaptive exploitation of historical directions.

Authors

Jiaxi Qian, Dong Shen, Samer S Saab

Published in

ISA transactions. Nov 03, 2026. Epub Nov 03, 2026.

Abstract

This paper proposes an accelerated iterative learning control framework for stochastic systems by incorporating an adaptive update direction mechanism. In this approach, a historical input term with its dedicated step size is adapted through a dimension-wise updating scheme. Unlike existing adaptive methods that solely adjust the learning gain, the proposed strategy adaptively rescales and refines each historical component, thereby enabling direction updates beyond simple proportional changes. Under mild conditions on the step sizes, convergence of the proposed method is rigorously established using a novel multi-parameter auxiliary-function analysis method. Furthermore, a one-step comparison of the weighted mean-square input error under sufficient conditions establishes the benefit of the adaptive historical direction. Numerical simulations are provided to validate the theoretical results.

PMID:
43009378
Bibliographic data and abstract were imported from PubMed on 11 Nov 2026.

Read full publication at:
Please sign in to see all details.

Stats

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.