On the Critic Intelligence for Discrete-Time Advanced Optimal Control Design

Abstract

AbstractThe idea of optimization can be regarded as an important basis of many disciplines and hence is extremely useful for a large number of research fields, particularly for artificial-intelligence-based advanced control design. Due to the difficulty of solving optimal control problems for general nonlinear systems, it is necessary to establish a kind of novel learning strategies with intelligent components. Besides, the rapid development of computer and networked techniques promotes the research on optimal control within the discrete-time domain. In this chapter, the bases, derivations, and recent progresses of critic intelligence for discrete-time advanced optimal control design are presented with an emphasis on the iterative framework. Among them, the so-called critic intelligence methodology is highlighted, which integrates learning approximators and the reinforcement formulation.KeywordsAdaptive criticAdvanced optimal controlDynamic systemsIntelligent criticReinforcement learning