Using Expectation-Maximization for Reinforcement Learning

Dayan, P; Hinton, GE

doi:10.1162/neco.1997.9.2.271

Local TagsRelease HistoryDetailsSummary

Using Expectation-Maximization for Reinforcement Learning

Dayan, P., & Hinton, G. (1997). Using Expectation-Maximization for Reinforcement Learning. Neural computation, 9(2), 271-278. doi:10.1162/neco.1997.9.2.271.

Item is Released

show all hide all

Basic

show hide

Item Permalink: https://hdl.handle.net/21.11116/0000-0002-D658-A Version Permalink: https://hdl.handle.net/21.11116/0000-0005-1A0D-1

Genre: Journal Article

Files

show Files

Locators

show

hide

Locator:
https://www.mitpressjournals.org/doi/10.1162/neco.1997.9.2.271 (Publisher version) Open Access status unknown

Description:
-

OA-Status:

Creators

show

hide

Creators:
Dayan, P¹, Author
Hinton, GE, Author

Affiliations:
1External Organizations, ou_persistent22

Content

show

hide

Free keywords: -

Abstract: We discuss Hinton's (1989) relative payoff procedure (RPP), a static reinforcement learning algorithm whose foundation is not stochastic gradient ascent. We show circumstances under which applying the RPP is guaranteed to increase the mean return, even though it can make large changes in the values of the parameters. The proof is based on a mapping between the RPP and a form of the expectation-maximization procedure of Dempster, Laird, and Rubin (1977).

Details

show

hide

Language(s):

Dates: Date issued: 1997-02

Publication Status: Issued

Pages: -

Publishing info: -

Table of Contents: -

Rev. Type: -

Identifiers: DOI: 10.1162/neco.1997.9.2.271

Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show

hide

Title: Neural computation

Source Genre: Journal

Creator(s):

Affiliations:

Publ. Info: Cambridge, Mass. : MIT Press

Pages: - Volume / Issue: 9 (2) Sequence Number: - Start / End Page: 271 - 278 Identifier: ISSN: 0899-7667
CoNE: https://pure.mpg.de/cone/journals/resource/954925561591