Learning From Human Feedback
Learning From Human Feedback is a computational learning paradigm within Human-Robot Interaction and Imitation Learning in which an agent acquires skills or refines behavior through direct supervision, evaluation, or corrective input provided by humans, distinguishing it from other learning paradigms by its reliance on explicit, real-time, or iterative feedback from human sources to guide or shape the learning process.
299
Publications
20.9K
Citations
1.2K
Authors
289
Institutions
Publications per year
2017–2026
213
Variants
Lfhf
299
Training language models to follow instructions with human feedback
Long Ouyang, Jeff Wu, Xu Jiang et al. · arXiv (Cornell University) · 2022 · 4.3K citations · Full text
Deep reinforcement learning from human preferences
Paul F. Christiano, Jan Leike, T. B. Brown et al. · arXiv (Cornell University) · 2017 · 508 citations · Full text
1–5 of 299
1.2K
9
h-index
9
h-index
9
h-index
9
h-index
7
h-index
1–5 of 1.2K
289
Stanford University
Stanford, United States
11 h-index
19 publications
1K citations
Georgia Institute of Technology
Atlanta, United States
10 h-index
22 publications
2.3K citations
The University of Texas at Austin
Austin, United States
9 h-index
20 publications
994 citations
Massachusetts Institute of Technology
Cambridge, United States
8 h-index
12 publications
801 citations

Delft University of Technology
Delft, The Netherlands
8 h-index
18 publications
336 citations
North Carolina State University
Raleigh, United States
6 h-index
12 publications
646 citations
University of Oxford
Oxford, United Kingdom
6 h-index
10 publications
169 citations

Washington State University
Pullman, United States
6 h-index
12 publications
646 citations
1–8 of 289
Repository · 71 publications · 8.7K citations
35
h-index
Conference · 7 publications · 302 citations
7
h-index
4 publications · 149 citations
4
h-index
4 publications · 92 citations
4
h-index
3 publications · 178 citations
3
h-index
1–5