Transcription of Dynamic Programming and Optimal Control 3rd Edition, …
{{id}} {{{paragraph}}}
Example: biology
Dynamic Programming and Optimal Control 3rd Edition, …
Dynamic Programming and Optimal Control3rd Edition, Volume IIbyDimitri P. BertsekasMassachusetts Institute of TechnologyChapter 6 Approximate Dynamic ProgrammingThis is an updated version of the research-oriented Chapter6 onApproximate Dynamic Programming . It will be periodically updated asnew research becomes available, and will replace the current Chapter 6 inthe book s next addition to editorial revisions, rearrangements, and new exercises,the chapter includes an account of new research, which is collected mostlyin Sections and Furthermore, a lot of new material has beenadded, such as an account of post-decision state simplifications ( ), regression-based TD methods (Section ), feature scaling ( ), policy oscillations (Section ), -policy iteration and explorationenhanced TD methods, aggregation methods (Section ), new Q-learningalgorithms (Section ), and Monte Carlo linear algebra (Section ).This chapter represents work in progress.
the projection of the vector T(Φr) on the subspace].† We can view Eq. (6.1) as a form of projected Bellman equation. We will show that for a special choice of the norm of the projection, ΠT is a contraction mapping, so the projected Bellman equation has a unique solution Φr∗. We will discuss several iterative methods for finding r∗ in
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: