Kernel Value Function Approximation
Kernel Value Function Approximation is a value function approximation method that employs kernel-based functions to represent and generalize value estimates in reinforcement learning, distinguishing itself by leveraging reproducing kernel Hilbert spaces to capture nonlinear relationships in state or state-action spaces.
18
Publications
730
Citations
47
Authors
23
Institutions
Publications per year
2017–2026
6
Parents
18
Kernelized value function approximation for reinforcement learning
Gavin Taylor, Ronald Parr · 2009 · 102 citations
1–5 of 18
47
2
h-index
2
h-index
2
h-index
2
h-index
2
h-index
1–5 of 47
23
Tokyo Institute of Technology
Tokyo, Japan
2 h-index
3 publications
87 citations
Max Planck Institute for Intelligent Systems
Stuttgart, Germany
2 h-index
3 publications
56 citations

McGill University
Montreal, Canada
2 h-index
6 publications
180 citations

University of Edinburgh
Edinburgh, United Kingdom
2 h-index
7 publications
168 citations

National University of Defense Technology
Changsha, China
2 h-index
9 publications
1.2K citations
Duke University
Durham, United States
1 h-index
2 publications
204 citations
SUNY Downstate Health Sciences University
Brooklyn, United States
1 h-index
1 publications
12 citations
University of Stuttgart
Stuttgart, Germany
1 h-index
2 publications
24 citations
1–8 of 23
2 publications · 224 citations
2
h-index
Repository · 2 publications · 40 citations
2
h-index
Conference · 1 publications · 17 citations
1
h-index
1 publications · 15 citations
1
h-index
Repository · 1 publications · 16 citations
1
h-index
1–5