Approximate Value Iteration
Approximate Value Iteration is a variant of the value iteration algorithm in reinforcement learning that replaces exact value function updates with approximate ones, typically using function approximation to handle large or continuous state spaces.
81
Publications
5.3K
Citations
163
Authors
92
Institutions
Publications per year
2017–2026
24
Parents
81
Approximately Optimal Approximate Reinforcement Learning
Sham M. Kakade, John Langford · 2002 · 595 citations
1–5 of 81
163
6
h-index
4
h-index
4
h-index
4
h-index
4
h-index
1–5 of 163
92
Stanford University
Stanford, United States
8 h-index
17 publications
1.4K citations

McGill University
Montreal, Canada
4 h-index
6 publications
151 citations

University of Alberta
Edmonton, Canada
4 h-index
5 publications
390 citations
Technion – Israel Institute of Technology
Haifa, Israel
4 h-index
6 publications
318 citations
Institut national de recherche en sciences et technologies du numérique
Le Chesnay-Rocquencourt, France
4 h-index
4 publications
195 citations
Meta (Israel)
Tel Aviv, Israel
3 h-index
3 publications
86 citations

Polytechnic University of Timişoara
Timișoara, Romania
3 h-index
6 publications
126 citations
University of California, Berkeley
Berkeley, United States
2 h-index
2 publications
117 citations
1–8 of 92
Repository · 6 publications · 301 citations
6
h-index
Repository · 5 publications · 231 citations
5
h-index
2 publications · 108 citations
2
h-index
2 publications · 34 citations
2
h-index
Repository · 2 publications · 91 citations
2
h-index
1–5