Artificial Neural Networks as Estimators for State Values and the Action Selection

Uwe Lorenz

Chapter 5 in Reinforcement Learning From Scratch, 2022, pp 123-173 from Springer

Abstract: Abstract Usually, the available resources are not sufficient to tabulate policy, valuation function, or model. Therefore, this chapter introduces parameterized estimators that allow us, for example, to estimate the valuation of states even if they have not been observed in exactly the same form before. In particular, the so-called artificial neural networks are discussed. We will also learn possibilities to use such estimators to create parameterized policies which, for a given state, can produce and improve a useful probability distribution over the available actions.

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_5

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

DOI: 10.1007/978-3-031-09030-1_5

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 ().