Neural Network for Multiobjective Dynamic Programming

A novel neural network is presented for solving multiobjective dynamic programming problems.The proposed neural network is proven to be Lyapunov stable and capable of generating noninferior solutions to the multiobjective dynamic programming problems.The asymptotic properties of the neural network are analyzed and the conditions for asymptotic stability,solution feasibility,and solution optimality are derived.The transient behavior of the neural network is simulated and the validity of the network is verified with numerical examples and case studies.