$ {H}_{ {\infty }}$ Tracking Control of Completely Unknown Continuous-Time Systems via Off-Policy Reinforcement Learning

By Hamidreza Modares, Frank L. Lewis, Zhong-Ping Jiang. IEEE Transactions on Neural Networks and Learning Systems, 2015

400 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.

Reinforcement learning for control: Performance, stability, and deep approximators (2018, background): “When it comes to adversarial agents, the game theoretic viewpoint is needed (Lewis et al., 2012; Modares et al., 2015; Russell and Norvig, 2016).”
Adaptive Dynamic Programming for Control: A Survey and Recent Advances (2021, methodology): “Compared with on-policy learning, it uses system data generated by arbitrary control to solve the HJB equation [123]–[131].”
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”