Self-supervised Policy Learning
Self-Supervised Policy Learning is a machine learning framework within robotics that enables policy acquisition through structuring learning objectives from unlabeled environmental interactions, distinguishing itself by eliminating the need for externally provided rewards or supervision.
95
Publications
5.2K
Citations
441
Authors
156
Institutions
Publications per year
2017–2026
85
95
Curiosity-Driven Exploration by Self-Supervised Prediction
Deepak Pathak, Pulkit Agrawal, Alexei A. Efros et al. · 2017 · 688 citations · Full text
1–5 of 95
441
7
h-index
5
h-index
4
h-index
4
h-index
3
h-index
1–5 of 441
156
University of California, Berkeley
Berkeley, United States
11 h-index
45 publications
4.3K citations
Google (United States)
Mountain View, United States
5 h-index
45 publications
7.8K citations
Stanford University
Stanford, United States
5 h-index
25 publications
872 citations

University of Toronto
Toronto, Canada
4 h-index
4 publications
88 citations
Meta (Israel)
Tel Aviv, Israel
4 h-index
7 publications
210 citations
Berkeley College
New York, United States
3 h-index
9 publications
566 citations
ETH Zurich
Zurich, Switzerland
3 h-index
8 publications
162 citations
University of Zurich
Zurich, Switzerland
3 h-index
6 publications
322 citations
1–8 of 156
Repository · 25 publications · 832 citations
15
h-index
4 publications · 720 citations
4
h-index
2 publications · 44 citations
2
h-index
2 publications · 37 citations
2
h-index
2 publications · 53 citations
2
h-index
1–5