Off-policy Reinforcement Learning
Off-Policy Reinforcement Learning is a reinforcement learning paradigm in which the agent learns the value function of a target policy using data generated by a different behavior policy, thereby enabling experience replay and improved data efficiency.
390
Publications
31K
Citations
888
Authors
266
Institutions
Publications per year
2017–2026
331
390
Deterministic policy gradient algorithms
David Silver, Guy Lever, Nicolas Heess et al. · HAL (Le Centre pour la Communication Scientifique Directe) · 2014 · 1.7K citations · Full text
Q-Learning Algorithms: A Comprehensive Classification and Applications
Beakcheol Jang, Myeonghwi Kim, Gaspard Harerimana et al. · IEEE Access · 2019 · 604 citations · Full text
The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games
Chao Yu, Akash Velu, Eugene Vinitsky et al. · arXiv (Cornell University) · 2021 · 594 citations · Full text
1–5 of 390
888
23
h-index
19
h-index
13
h-index
12
h-index
12
h-index
1–5 of 888
266
Google (United States)
Mountain View, United States
26 h-index
145 publications
9K citations
The University of Texas at Arlington
Arlington, United States
18 h-index
35 publications
4.8K citations

Northeastern University
Shenyang, China
17 h-index
36 publications
4.3K citations

University of Alberta
Edmonton, Canada
15 h-index
36 publications
2.7K citations
University of California, Berkeley
Berkeley, United States
14 h-index
38 publications
5.7K citations

University of Science and Technology Beijing
Beijing, China
10 h-index
18 publications
2.1K citations

McGill University
Montreal, Canada
10 h-index
15 publications
1.8K citations
Massachusetts Institute of Technology
Cambridge, United States
10 h-index
13 publications
806 citations
1–8 of 266
Repository · 151 publications · 12.9K citations
50
h-index
19 publications · 3.3K citations
19
h-index
18 publications · 1.9K citations
16
h-index
Conference · 8 publications · 453 citations
8
h-index
Conference · 8 publications · 852 citations
8
h-index
1–5