Online Value Iteration
Online Value Iteration is a dynamic programming algorithm that incrementally updates value estimates in real-time using newly observed transitions, distinguishing it from batch or offline variants by its immediate incorporation of experience into the value function without requiring complete environment models or full iterations over the state space.
39
Publications
2.4K
Citations
107
Authors
58
Institutions
Publications per year
2017–2026
23
Parents
39
1–5 of 39
107
5
h-index
3
h-index
3
h-index
2
h-index
2
h-index
1–5 of 107
58

Northeastern University
Shenyang, China
4 h-index
16 publications
893 citations
The University of Texas at Arlington
Arlington, United States
4 h-index
6 publications
818 citations

Beijing University of Technology
Beijing, China
3 h-index
6 publications
147 citations
Robotics Research (United States)
Cincinnati, United States
2 h-index
4 publications
88 citations
University of Virginia
Charlottesville, United States
2 h-index
4 publications
304 citations

Kyonggi University
Suwon, South Korea
2 h-index
2 publications
24 citations

Florida Institute of Technology
Melbourne, United States
2 h-index
2 publications
261 citations
Nanjing University of Posts and Telecommunications
Nanjing, China
2 h-index
4 publications
260 citations
1–8 of 58
4 publications · 290 citations
4
h-index
4 publications · 479 citations
4
h-index
2 publications · 338 citations
2
h-index
1 publications · 10 citations
1
h-index
1 publications · 72 citations
1
h-index
1–5