Multi-task Imitation Learning
Multi-Task Imitation Learning is a framework within imitation learning that enables a single policy to acquire multiple distinct tasks from expert demonstrations by jointly learning shared representations and task-specific behaviors.
15
Publications
610
Citations
56
Authors
26
Institutions
Publications per year
2017–2026
13
Parents
15
Multi-task Learning with Attention for End-to-end Autonomous Driving
Keishi Ishihara, Anssi Kanervisto, Jun Miura et al. · 2021 · 80 citations
1–5 of 15
56
2
h-index
2
h-index
2
h-index
2
h-index
2
h-index
1–5 of 56
26
Stanford University
Stanford, United States
2 h-index
5 publications
337 citations
Corvallis Environmental Center
Corvallis, United States
2 h-index
10 publications
700 citations

Shanghai Jiao Tong University
Shanghai, China
2 h-index
2 publications
120 citations
University of California, Berkeley
Berkeley, United States
2 h-index
8 publications
204 citations
Institute of Intelligent Machines
Hefei, China
1 h-index
1 publications
40 citations
Toyohashi University of Technology
Toyohashi, Japan
1 h-index
2 publications
160 citations
Finland University
Helsinki, Finland
1 h-index
3 publications
240 citations
College of San Mateo
San Mateo, United States
1 h-index
1 publications
25 citations
1–8 of 26
Repository · 2 publications · 32 citations
2
h-index
1 publications · 40 citations
1
h-index
ITIVBL · 1 publications · 23 citations
1
h-index
1 publications · 16 citations
1
h-index
1 publications · 31 citations
1
h-index
1–5