We discuss a variety of adaptive critic designs (ACDs) for neurocontrol. These are suitable for learning in noisy, nonlinear, and nonstationary environments. They have common roots as generalizations of dynamic programming for neural reinforcement learning approaches. Our discussion of these origins leads to an explanation of three design families: heuristic dynamic programming, dual heuristic programming, and globalized dual heuristic programming (GDHP). The main emphasis is on DHP and GDHP as advanced ACDs. We suggest two new modifications of the original GDHP design that are currently the only working implementations of GDHP. They promise to be useful for many engineering applications in the areas of optimization and optimal control. Based on one of these modifications, we present a unified approach to all ACDs. This leads to a generalized training procedure for ACDs


Electrical and Computer Engineering

Keywords and Phrases

Adaptive Control; Adaptive Critic Designs; Backpropagation; Duality (Mathematics); Dynamic Programming; Generalisation (Artificial Intelligence); Generalizations; Generalized Training Procedure; Globalized Dual Heuristic Programming; Heuristic Programming; Neural Nets; Neurocontrol; Neurocontrollers; Optimal Control; Optimization; Reinforcement Learning

International Standard Serial Number (ISSN)


Document Type

Article - Conference proceedings

Document Version

Final Version

File Type





© 1997 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.

Full Text Link