Optimal Adaptive Control and Differential Games by Reinforcement Learning Principles

Draguna Vrabie is a Senior Research Scientist at United Technologies Research Center, East Hartford, Connecticut.Kyriakos G. Vamvoudakis is a Faculty Project Research Scientist at the Center for Control, Dynamical-Systems, and Computation (CCDC), Dept of Electrical and Computer Eng., University of California, Santa Barbara.Frank L. Lewis is the Moncrief-O'Donnell Endowed Chair at the UTA Research Institute, University of Texas at Arlington.

• Chapter 1: Introduction to optimal control, adaptive control and reinforcement learningChapter 2: Reinforcement learning and optimal control of discrete-time systems: Using natural decision methods to design optimal adaptive controllersPart I: Optimal adaptive control using reinforcement learning structuresChapter 3: Optimal adaptive control using integral reinforcement learning for linear systemsChapter 4: Integral reinforcement learning (IRL) for non-linear continuous-time systemsChapter 5: Generalized policy iteration for continuous-time systemsChapter 6: Value iteration for continuous-time systemsPart II: Adaptive control structures based on reinforcement learningChapter 7: Optimal adaptive control using synchronous online learningChapter 8: Synchronous online learning with integral reinforcementPart III: Online differential games using reinforcement learningChapter 9: Synchronous online learning for zero-sum two-player games and H-infinity controlChapter 10: Synchronous online learning for multiplayer non-zero-sum gamesChapter 11: Integral reinforcement learning for zero-sum two-player gamesAppendix A: Proofs