Least-squares Temporal-difference Learning
Least-Squares Temporal-Difference Learning is a value function approximation method that minimizes the Bellman error of temporal-difference updates in a least-squares sense through linear regression, distinguishing itself from other temporal-difference algorithms by solving for parameter updates analytically rather than incrementally.
44
Publications
3.6K
Citations
90
Authors
53
Institutions
Publications per year
2017–2026
9
Variants
Lstd
44
Practical issues in temporal difference learning
Gerald Tesauro · Machine Learning · 1992 · 800 citations · Full text
Technical Update: Least-Squares Temporal Difference Learning
Justin A. Boyan · Machine Learning · 2002 · 299 citations · Full text
Least-Squares Temporal Difference Learning
Justin A. Boyan · 1999 · 262 citations
1–5 of 44
90
5
h-index
3
h-index
3
h-index
3
h-index
2
h-index
1–5 of 90
53

University of Alberta
Edmonton, Canada
4 h-index
6 publications
352 citations
Boston University
Boston, United States
3 h-index
9 publications
189 citations

National University of Defense Technology
Changsha, China
3 h-index
7 publications
1.2K citations
Duke University
Durham, United States
2 h-index
3 publications
279 citations

Beijing University of Chemical Technology
Beijing, China
2 h-index
7 publications
124 citations
Centre Inria de l'Université de Lille
Villeneuve-d'Ascq, France
2 h-index
4 publications
255 citations
Institut national de recherche en sciences et technologies du numérique
Le Chesnay-Rocquencourt, France
2 h-index
4 publications
255 citations
IBM Research - Thomas J. Watson Research Center
Yorktown Heights, United States
2 h-index
2 publications
839 citations
1–8 of 53
4 publications · 1.5K citations
4
h-index
Repository · 3 publications · 97 citations
3
h-index
Conference · 2 publications · 21 citations
2
h-index
2 publications · 35 citations
2
h-index
Repository · 2 publications · 167 citations
2
h-index
1–5