Neural-network-based discounted optimal control via an integrated value iteration with accuracy guarantee
Mingming Ha, Ding Wang, Derong Liu
Topics & Concepts
Artificial neural networkGradient descentComputer scienceStability (learning theory)Mathematical optimizationNonlinear systemValue (mathematics)Function approximationFunction (biology)Lyapunov functionBellman equationControl theory (sociology)AlgorithmMathematicsControl (management)Artificial intelligenceMachine learningPhysicsEvolutionary biologyQuantum mechanicsBiologyAdaptive Dynamic Programming ControlAdaptive Control of Nonlinear SystemsControl Systems and Identification