Reinforcement Learning for Optimal Feedback Control by Rushikesh Kamalapurkar Patrick Walters Joel Rosenfeld & Warren Dixon

Author:Rushikesh Kamalapurkar, Patrick Walters, Joel Rosenfeld & Warren Dixon
Language: eng
Format: epub
Publisher: Springer International Publishing, Cham

(4.36)

The saturated least-squares update law in (4.34) ensures that there exist positive constants such that Using the bounds on and and the fact that , the candidate Lyapunov function in (4.36) can be bounded as

(4.37)

and , where and are class functions.

Given any compact set containing an open ball of radius centered at the origin, a positive constant is defined as

(4.38)

where and . Let be a class function such that

(4.39)

The sufficient gain conditions used in the subsequent Theorem 4.6 are

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.