Paper
22 March 1999 Stable adaptive control using new critic designs
Author Affiliations +
Proceedings Volume 3728, Ninth Workshop on Virtual Intelligence/Dynamic Neural Networks; (1999) https://doi.org/10.1117/12.343068
Event: Ninth Workshop on Virtual Intelligence/Dynamic Neural Networks: Neural Networks Fuzzy Systems, Evolutionary Systems and Virtual Re, 1998, Stockholm, Sweden
Abstract
Classical adaptive control proves total-system stability for control of linear plants, but only for plants meeting very restrictive assumptions. Approximate Dynamic Programming (ADP) has the potential, in principle, to ensure stability without such tight restrictions. It also offers nonlinear and neural extensions for optimal control, with empirically supported links to what is seen in the brain. However, the relevant ADP methods in use today--TD, HDP, DHP, GDHP--and the Galerkin-based versions of these all have serious limitations when used here as parallel distributed real-time learning systems; either they do not possess quadratic unconditional stability (to be defined) or they lead to incorrect results in the stochastic case. (ADAC or Q- learning designs do not help.) After explaining these conclusions, this paper describes new ADP designs which overcome these limitations. It also addresses the Generalized Moving Target problem, a common family of static optimization problems, and describes a way to stabilize large-scale economic equilibrium models, such as the old long-term energy mode of DOE.
© (1999) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Paul J. Werbos "Stable adaptive control using new critic designs", Proc. SPIE 3728, Ninth Workshop on Virtual Intelligence/Dynamic Neural Networks, (22 March 1999); https://doi.org/10.1117/12.343068
Lens.org Logo
CITATIONS
Cited by 54 scholarly publications.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Stochastic processes

Adaptive control

Matrices

Computer programming

Neural networks

Control systems

Error analysis

Back to Top