Demonstration-based Policy Learning
Demonstration-Based Policy Learning is a machine learning framework that acquires a policy through the observation of expert demonstrations, distinguished by its reliance on behavioral examples rather than explicit reward signals or environment interactions.
178
Publications
7.4K
Citations
513
Authors
149
Institutions
Publications per year
2017–2026
120
Variants
Learning From Demonstration
Parents
178
Policy entrepreneurs and school choice
Choice Reviews Online · 2001 · 370 citations
Learning for control from multiple demonstrations
Adam Coates, Pieter Abbeel, Andrew Y. Ng · 2008 · 235 citations
1–5 of 178
513
11
h-index
9
h-index
7
h-index
5
h-index
5
h-index
1–5 of 513
149
Carnegie Mellon University
Pittsburgh, United States
12 h-index
24 publications
1.4K citations
University of California, Berkeley
Berkeley, United States
11 h-index
35 publications
1.3K citations
Stanford University
Stanford, United States
9 h-index
23 publications
2K citations
Georgia Institute of Technology
Atlanta, United States
8 h-index
21 publications
1.4K citations
École Polytechnique Fédérale de Lausanne
Lausanne, Switzerland
5 h-index
8 publications
228 citations
The University of Texas at Austin
Austin, United States
5 h-index
9 publications
340 citations
Nanyang Technological University
Singapore, Singapore
4 h-index
12 publications
876 citations
Max Planck Society
Munich, Germany
4 h-index
6 publications
137 citations
1–8 of 149
Repository · 37 publications · 1.2K citations
18
h-index
Conference · 8 publications · 266 citations
8
h-index
6 publications · 162 citations
6
h-index
4 publications · 157 citations
5
h-index
3 publications · 290 citations
3
h-index
1–5