Offline Model-based Reinforcement Learning
Offline Model-Based Reinforcement Learning is a model-based reinforcement learning paradigm that leverages pre-collected, static datasets to learn environment dynamics and policies without online environment interaction.
34
Publications
1.5K
Citations
116
Authors
52
Institutions
Publications per year
2017–2026
33
Parents
34
MOPO: Model-based Offline Policy Optimization
Tianhe Yu, Garrett Thomas, Lantao Yu et al. · arXiv (Cornell University) · 2020 · 217 citations · Full text
MOReL : Model-Based Offline Reinforcement Learning
Rahul Kidambi, Aravind Rajeswaran, Praneeth Netrapalli et al. · arXiv (Cornell University) · 2020 · 158 citations · Full text
Silvio Brandi, Massimo Fiorentini, Alfonso Capozzoli · Automation in Construction · 2022 · 99 citations · Full text
Engineering, Computational Engineering, Mechanical Engineering +16
1–5 of 34
116
4
h-index
4
h-index
4
h-index
4
h-index
3
h-index
1–5 of 116
52

Cornell University
Ithaca, United States
3 h-index
4 publications
77 citations

Beijing Institute of Technology
Beijing, China
3 h-index
15 publications
610 citations
University of California, Berkeley
Berkeley, United States
3 h-index
5 publications
175 citations
Google (United States)
Mountain View, United States
3 h-index
6 publications
324 citations

Xidian University
Xi'an, China
2 h-index
3 publications
146 citations
Stanford University
Stanford, United States
2 h-index
10 publications
415 citations
Chinese University of Hong Kong
Hong Kong, Hong Kong
2 h-index
2 publications
42 citations
University of Washington
Seattle, United States
2 h-index
2 publications
70 citations
1–8 of 52
Repository · 11 publications · 591 citations
11
h-index
Conference · 2 publications · 74 citations
2
h-index
2 publications · 52 citations
2
h-index
1 publications · 32 citations
1
h-index
1 publications · 24 citations
1
h-index
1–5