Deep Imitation Learning
Deep Imitation Learning is a machine learning framework within the broader domain of Imitation Learning that leverages deep neural networks to map high-dimensional sensory inputs to actions by learning policies directly from expert demonstrations.
175
Publications
12.5K
Citations
662
Authors
198
Institutions
Publications per year
2017–2026
171
175
Xue Bin Peng, Pieter Abbeel, Sergey Levine et al. · ACM Transactions on Graphics · 2018 · 803 citations · Full text
1–5 of 175
662
8
h-index
8
h-index
6
h-index
Hong Kong University of Science and Technology, Hong Kong SAR China
5 publications · 292 citations
5
h-index
5
h-index
1–5 of 662
198
University of California, Berkeley
Berkeley, United States
8 h-index
36 publications
6.7K citations

Hong Kong University of Science and Technology
Hong Kong, Hong Kong
7 h-index
26 publications
1.3K citations

Chinese Academy of Sciences
Beijing, China
5 h-index
22 publications
1.1K citations
The University of Tokyo
Tokyo, Japan
5 h-index
13 publications
434 citations
Georgia Institute of Technology
Atlanta, United States
5 h-index
14 publications
1.4K citations
Google (United States)
Mountain View, United States
4 h-index
11 publications
640 citations
Beijing Academy of Artificial Intelligence
Beijing, China
4 h-index
14 publications
915 citations
University of Chinese Academy of Sciences
Beijing, China
4 h-index
14 publications
915 citations
1–8 of 198
Repository · 35 publications · 1.5K citations
19
h-index
10 publications · 504 citations
10
h-index
TOG · 5 publications · 1.3K citations
5
h-index
5 publications · 147 citations
5
h-index
Conference · 4 publications · 281 citations
4
h-index
1–5