Policy Iteration Complexity is a theoretical construct in reinforcement learning that characterizes the computational complexity of the policy iteration algorithm in terms of the number of iterations required to converge to an optimal policy under a given decision-making framework.
29
Publications
1.3K
Citations
59
Authors
37
Institutions
Publications per year
2017–2026
10
Parents
Publications
29
Optimal control of Boolean control networks with average cost: A policy iteration approach
Yuhu Wu, Xi‐Ming Sun, Xudong Zhao et al. · Automatica · 2018 · 194 citations
On the Complexity of Policy Iteration
Yishay Mansour, Satinder Singh · arXiv (Cornell University) · 2013 · 76 citations · Full text
1–5 of 29
Authors
59
- OM
2
h-index
- KK
2
h-index
- PL
2
h-index
- BR
2
h-index
- GL
2
h-index
1–5 of 59
Institutions
37
University of Alberta
Edmonton, Canada
3 h-index
3 publications
95 citations
University of Waterloo
Waterloo, Canada
2 h-index
4 publications
113 citations
Massachusetts Institute of Technology
Cambridge, United States
2 h-index
2 publications
399 citations
University of California, Berkeley
Berkeley, United States
2 h-index
5 publications
170 citations
Decision Systems (United States)
Northbrook, United States
1 h-index
2 publications
82 citations
Université de Lorraine
Nancy, France
1 h-index
1 publications
10 citations
Shandong Institute of Automation
Jinan, China
1 h-index
2 publications
32 citations
University of Kentucky
Lexington, United States
1 h-index
1 publications
29 citations
1–8 of 37
Venues
- Journal of Mathematical Analysis and Applications
3 publications · 57 citations
3
h-index
- arXiv (Cornell University)
Repository · 2 publications · 98 citations
2
h-index
- Automatica
2 publications · 247 citations
2
h-index
- Machine Learning
1 publications · 32 citations
1
h-index
- Journal of Artificial Intelligence Research
JAIR · 1 publications · 15 citations
1
h-index
1–5