Adaptive optimization algorithm for nonlinear Markov jump systems with partial unknown dynamics

Haiyang Fang, Guozheng Zhu, Vladimir Stojanović, Rong Nie, Shuping He, Xiaoli Luan, Fei Liu

2021International Journal of Robust and Nonlinear Control103 citationsDOI

Abstract

Abstract An online adaptive optimal control problem for a class of nonlinear Markov jump systems (MJSs) is studied. It is worth noting that the dynamic information of MJSs is partially unknown. Applying the neural network linear differential inclusion techniques, the nonlinear terms in MJSs are approximately converted to linear forms. By using subsystem transformation schemes, we can transfer the nonlinear MJSs to N new coupled linear subsystems. Then a new online policy iteration algorithm is put forward to obtain the adaptive optimal controller. Some theorems are given afterward to ensure the convergence of the new algorithm. At last, a simulation example is provided to verify the applicability of the algorithm.

Topics & Concepts

Nonlinear systemConvergence (economics)Computer scienceMarkov chainJumpControl theory (sociology)Controller (irrigation)Mathematical optimizationTransformation (genetics)AlgorithmClass (philosophy)Markov processArtificial neural networkMathematicsControl (management)Artificial intelligenceMachine learningGeneEconomicsStatisticsBiologyPhysicsQuantum mechanicsBiochemistryEconomic growthChemistryAgronomyAdaptive Dynamic Programming ControlAdaptive Control of Nonlinear SystemsReinforcement Learning in Robotics