Proximal Policy Optimization
Proximal Policy Optimization is a policy gradient reinforcement learning algorithm that belongs to the class of trust-region optimization methods, distinguished by its use of clipped probability ratios to stabilize training through limited step sizes without requiring manual tuning of learning rates.
501
Publications
32.9K
Citations
1.9K
Authors
560
Institutions
Publications per year
2017–2026
501
Parents
501
Junyoung Park, Jaehyeong Chun, Youngkook Kim et al. · International Journal of Production Research · 2021 · 308 citations · Full text
1–5 of 501
1.9K
7
h-index
6
h-index
6
h-index
6
h-index
5
h-index
1–5 of 1.9K
560
Tsinghua University
Beijing, China
15 h-index
59 publications
3.1K citations

Beijing University of Posts and Telecommunications
Beijing, China
13 h-index
38 publications
1.2K citations
Kyung Hee University
Seoul, South Korea
11 h-index
36 publications
1.4K citations
Google (United States)
Mountain View, United States
10 h-index
19 publications
1K citations

Huazhong University of Science and Technology
Wuhan, China
10 h-index
29 publications
2K citations

Imperial College London
London, United Kingdom
9 h-index
21 publications
862 citations

Southeast University
Nanjing, China
9 h-index
22 publications
1K citations

Beijing Institute of Technology
Beijing, China
9 h-index
26 publications
1.2K citations
1–8 of 560
Repository · 52 publications · 13.4K citations
26
h-index
29 publications · 1.1K citations
21
h-index
17 publications · 1.2K citations
16
h-index
17 publications · 566 citations
15
h-index
13 publications · 910 citations
12
h-index
1–5