Optimal Decision-Making in a Known Environment

Uwe Lorenz

Chapter 3 in Reinforcement Learning From Scratch, 2022, pp 23-46 from Springer

Abstract: Abstract This section describes how to compute an optimal action strategy for an environment with a finite number of states and action possibilities. You will learn the difference between an off-policy and an on-policy evaluation of state transitions. Value iteration and iterative tactic search techniques will be introduced and applied and tried in practice scenarios using the Java Hamster. Iterative tactic search, as a mutual improvement of evaluation and control, is introduced as a generalizable strategy for finding optimal behavior. Furthermore, the basics of computing optimal moves in a manageable board game scenario with adversaries are described.

Date: 2022
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-031-09030-1_3

Ordering information: This item can be ordered from
http://www.springer.com/9783031090301

DOI: 10.1007/978-3-031-09030-1_3

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().