Near-Optimal Control for Nonzero-Sum Differential Games of Continuous-Time Nonlinear Systems Using Single-Network ADP

By Huaguang Zhang, Lili Cui, Yanhong Luo. IEEE Transactions on Cybernetics, 2013

419 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Data-Driven Optimal Consensus Control for Discrete-Time Multi-Agent Systems With Unknown Dynamics Using Reinforcement Learning Method (2017, methodology): “Among these classical RL methods, ADP is regarded as one of the core methodologies to achieve optimal control policies for diversities of optimal control issues, such as optimal control with constrained control input [16]–[19], optimal tracking control [20]–[24], optimal control with time delays [25”
Observer-Based Neuro-Adaptive Optimized Control of Strict-Feedback Nonlinear Systems With State Constraints (2021, background): “Assumption 1 [19], [22], [46]: Assume that all the states (except output y ) are immeasurable and constrained in the compact sets, i.e., | x i | < k c i , where k c i is a known positive constant.”
Fuzzy Approximation-Based Adaptive Backstepping Optimal Control for a Class of Nonlinear Discrete-Time Systems With Dead-Zone (2016, background): “The nonzero-sum differential games of nonlinear continuous-time systems were solved in [17] by developing a near-optimal control scheme, in which the optimal control policies are obtained based on the single-network adaptive dynamic programming (ADP).”
Reinforcement-Learning-Based Robust Controller Design for Continuous-Time Uncertain Nonlinear Systems Subject to Input Constraints (2015, methodology): “The assumption is a common technique, which has been used in [15], [25], [45], and [52].”