Reinforcement Learning for Optimal Feedback Control

A Lyapunov-Based Approach

Nonfiction, Science & Nature, Technology, Automation, Mathematics, Calculus
Cover of the book Reinforcement Learning for Optimal Feedback Control by Rushikesh Kamalapurkar, Patrick Walters, Joel Rosenfeld, Warren Dixon, Springer International Publishing
View on Amazon View on AbeBooks View on Kobo View on B.Depository View on eBay View on Walmart
Author: Rushikesh Kamalapurkar, Patrick Walters, Joel Rosenfeld, Warren Dixon ISBN: 9783319783840
Publisher: Springer International Publishing Publication: May 10, 2018
Imprint: Springer Language: English
Author: Rushikesh Kamalapurkar, Patrick Walters, Joel Rosenfeld, Warren Dixon
ISBN: 9783319783840
Publisher: Springer International Publishing
Publication: May 10, 2018
Imprint: Springer
Language: English

Reinforcement Learning for Optimal Feedback Control develops model-based and data-driven reinforcement learning methods for solving optimal control problems in nonlinear deterministic dynamical systems. In order to achieve learning under uncertainty, data-driven methods for identifying system models in real-time are also developed. The book illustrates the advantages gained from the use of a model and the use of previous experience in the form of recorded data through simulations and experiments. The book’s focus on deterministic systems allows for an in-depth Lyapunov-based analysis of the performance of the methods described during the learning phase and during execution.

To yield an approximate optimal controller, the authors focus on theories and methods that fall under the umbrella of actor–critic methods for machine learning. They concentrate on establishing stability during the learning phase and the execution phase, and adaptive model-based and data-driven reinforcement learning, to assist readers in the learning process, which typically relies on instantaneous input-output measurements.

This monograph provides academic researchers with backgrounds in diverse disciplines from aerospace engineering to computer science, who are interested in optimal reinforcement learning functional analysis and functional approximation theory, with a good introduction to the use of model-based methods. The thorough treatment of an advanced treatment to control will also interest practitioners working in the chemical-process and power-supply industry.

View on Amazon View on AbeBooks View on Kobo View on B.Depository View on eBay View on Walmart

Reinforcement Learning for Optimal Feedback Control develops model-based and data-driven reinforcement learning methods for solving optimal control problems in nonlinear deterministic dynamical systems. In order to achieve learning under uncertainty, data-driven methods for identifying system models in real-time are also developed. The book illustrates the advantages gained from the use of a model and the use of previous experience in the form of recorded data through simulations and experiments. The book’s focus on deterministic systems allows for an in-depth Lyapunov-based analysis of the performance of the methods described during the learning phase and during execution.

To yield an approximate optimal controller, the authors focus on theories and methods that fall under the umbrella of actor–critic methods for machine learning. They concentrate on establishing stability during the learning phase and the execution phase, and adaptive model-based and data-driven reinforcement learning, to assist readers in the learning process, which typically relies on instantaneous input-output measurements.

This monograph provides academic researchers with backgrounds in diverse disciplines from aerospace engineering to computer science, who are interested in optimal reinforcement learning functional analysis and functional approximation theory, with a good introduction to the use of model-based methods. The thorough treatment of an advanced treatment to control will also interest practitioners working in the chemical-process and power-supply industry.

More books from Springer International Publishing

Cover of the book Nonlinearly Perturbed Semi-Markov Processes by Rushikesh Kamalapurkar, Patrick Walters, Joel Rosenfeld, Warren Dixon
Cover of the book Prevention of Cardiovascular Diseases by Rushikesh Kamalapurkar, Patrick Walters, Joel Rosenfeld, Warren Dixon
Cover of the book Algorithmic Advances in Riemannian Geometry and Applications by Rushikesh Kamalapurkar, Patrick Walters, Joel Rosenfeld, Warren Dixon
Cover of the book Confronting Gun Violence in America by Rushikesh Kamalapurkar, Patrick Walters, Joel Rosenfeld, Warren Dixon
Cover of the book Energetics of Muscular Exercise by Rushikesh Kamalapurkar, Patrick Walters, Joel Rosenfeld, Warren Dixon
Cover of the book Neurotransmitter Interactions and Cognitive Function by Rushikesh Kamalapurkar, Patrick Walters, Joel Rosenfeld, Warren Dixon
Cover of the book Quantum Walks and Search Algorithms by Rushikesh Kamalapurkar, Patrick Walters, Joel Rosenfeld, Warren Dixon
Cover of the book Privacy and Identity Management for the Future Internet in the Age of Globalisation by Rushikesh Kamalapurkar, Patrick Walters, Joel Rosenfeld, Warren Dixon
Cover of the book Precision Molecular Pathology of Uterine Cancer by Rushikesh Kamalapurkar, Patrick Walters, Joel Rosenfeld, Warren Dixon
Cover of the book Making Sense of Quantum Mechanics by Rushikesh Kamalapurkar, Patrick Walters, Joel Rosenfeld, Warren Dixon
Cover of the book Memristor Networks by Rushikesh Kamalapurkar, Patrick Walters, Joel Rosenfeld, Warren Dixon
Cover of the book Convention on International Civil Aviation by Rushikesh Kamalapurkar, Patrick Walters, Joel Rosenfeld, Warren Dixon
Cover of the book Predator–Prey Interactions: Co-evolution between Bats and Their Prey by Rushikesh Kamalapurkar, Patrick Walters, Joel Rosenfeld, Warren Dixon
Cover of the book The Evolution and Significance of the Cuban Revolution by Rushikesh Kamalapurkar, Patrick Walters, Joel Rosenfeld, Warren Dixon
Cover of the book Complex Magnetic Nanostructures by Rushikesh Kamalapurkar, Patrick Walters, Joel Rosenfeld, Warren Dixon
We use our own "cookies" and third party cookies to improve services and to see statistical information. By using this website, you agree to our Privacy Policy