Most of the literature on Reinforcement Learning discuss Hamilton Jacobi Bellman equations for optimality. In dynamics however Ricatti equations are used. I am curious if there are any parallels between the two equations for optimality? How do one differ from the other?
$\begingroup$
$\endgroup$
5
-
$\begingroup$ Hi: ricatti results from kalman filter theory. hjb results from optimal control theory. not sure of the relation but, if there is one, it's not obvious. I would google for them together and see if anything pops up. $\endgroup$– mark leedsCommented Jun 30, 2020 at 16:23
-
$\begingroup$ @markleeds What I read is ricatti also results from optimal control. This is why I was trying to find a link between the two. Will keep looking, thanks. $\endgroup$– GENIVI-LEARNERCommented Jun 30, 2020 at 18:02
-
$\begingroup$ that's news to me but it definitely then indicates a serious connection. there should be a ton of material out there for sure. I'm sorry that I can't be of more help. $\endgroup$– mark leedsCommented Jun 30, 2020 at 19:22
-
1$\begingroup$ Hi: I don't have time to read it but his talks about solving a differential riccati and then using that to solve hjb. ocw.mit.edu/courses/aeronautics-and-astronautics/… $\endgroup$– mark leedsCommented Jun 30, 2020 at 19:23
-
$\begingroup$ @markleeds thanks a lot. I will give it a read. $\endgroup$– GENIVI-LEARNERCommented Jul 1, 2020 at 12:11
Add a comment
|