Adaptive optimal control for continuous-time linear systems based on policy iteration

By Draguna L. Vrabie, Octavian C. Pastravanu, Murad Abu-Khalaf, Frank L. Lewis. at - Automatisierungstechnik, 2009

916 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/73a04faf268a5007940a492012ac55babefd556c

How researchers see this paper

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

In Computational Theory and Mathematics

In Electrical and Electronic Engineering

Citations in the corpus

Online actor critic algorithm to solve the continuous-time infinite horizon optimal control problem (2009, methodology): “Adaptive critics have been described in [14] for discrete-time systems and [2], [7], [17], [ 18 ] for continuous-time systems.”
Optimal tracking control of nonlinear partially-unknown constrained-input systems using integral reinforcement learning (2014, methodology): “Later, inspired by Vrabie and Lewis (2009) and Vrabie et al. (2009), some online PI algorithms were presented to solve the optimal regulation problem for completely unknown linear systems (Jiang & Jiang, 2012; Lee, Park, & Choi, 2012).”
$ {H}_{ {\infty }}$ Tracking Control of Completely Unknown Continuous-Time Systems via Off-Policy Reinforcement Learning (2015, methodology): “[36] used an integral RL (IRL) algorithm [15], [16] to learn the solution to the HJI equation for systems with unknown dynamics.”
Reinforcement learning and adaptive dynamic programming for feedback control (2009, background): “The minimization in (79) is given by (77) and can be more explicitly computed given the basis activation functions selected for the NN.”
Optimal Adaptive Control and Differential Games by Reinforcement Learning Principles (2012, methodology): “3.1.1 Policy iteration algorithm using integral reinforcement This section presents a new policy iteration algorithm that solves online for the optimal control gain (3.4) without using knowledge of the system matrix A (Vrabie et al., 2008, 2009; Vrabie, 2009; Vrabie and Lewis, 2009).”
Computational adaptive optimal control for continuous-time linear systems with completely unknown dynamics (2012, methodology): “An exact method was developed in Vrabie et al. (2009), where neither knowing the internal sys-tem dynamics nor measuring the state derivatives was necessary.”
Multi-agent differential graphical games (2011, background): “Policy Iteration techniques have been developed for continuous-time systems in [36].”
Adaptive Dynamic Programming for Control: A Survey and Recent Advances (2021, background): “It is worth mentioning that the success of PI depends on the initial admissible control policy, which makes the system stable in the learning process, and thus has been used by many researchers [70]–[75].”