English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  The Convergence of TD(λ) for General λ

Dayan, P. (1992). The Convergence of TD(λ) for General λ. Machine Learning, 8(3-4), 341-362. doi:10.1023/A:1022632907294.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/21.11116/0000-0002-D743-0 Version Permalink: http://hdl.handle.net/21.11116/0000-0002-D744-F
Genre: Journal Article

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Dayan, P1, Author              
Affiliations:
1External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: The method of temporal differences (TD) is one way of making consistent predictions about the future. This paper uses some analysis of Watkins (1989) to extend a convergence theorem due to Sutton (1988) from the case which only uses information from adjacent time steps to that involving information from arbitrary ones. It also considers how this version of TD behaves in the face of linearly dependent representations for states—demonstrating that it still converges, but to a different answer from the least mean squares algorithm. Finally it adapts Watkins' theorem that Q -learning, his closely related prediction and action learning method, converges with probability one, to demonstrate this strong form of convergence for a slightly modified version of TD.

Details

show
hide
Language(s):
 Dates: 1992-05
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1023/A:1022632907294
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Machine Learning
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Dordrecht : Springer
Pages: - Volume / Issue: 8 (3-4) Sequence Number: - Start / End Page: 341 - 362 Identifier: ISSN: 0885-6125
CoNE: https://pure.mpg.de/cone/journals/resource/08856125