Interactive Reinforcement Learning
Interactive Reinforcement Learning is a machine learning framework in which an agent learns optimal behaviors through sequential decision-making interactions with a human or environment, distinguished by the integration of real-time feedback during the learning process to accelerate convergence and improve policy adaptation.
86
Publications
3.9K
Citations
219
Authors
85
Institutions
Publications per year
2017–2026
59
86
Interactively shaping agents via human reinforcement
W. Bradley Knox, Peter Stone · 2009 · 414 citations
Policy Shaping: Integrating Human Feedback with Reinforcement Learning
Shane Griffith, K.A. Subramanian, Jonathan Scholz et al. · 2013 · 305 citations
1–5 of 86
219
10
h-index
6
h-index
5
h-index
4
h-index
4
h-index
1–5 of 219
85
Universidad Central de Chile
Santiago, Chile
7 h-index
11 publications
300 citations
Universität Hamburg
Hamburg, Germany
5 h-index
19 publications
973 citations
Hamburg University of Technology
Hamburg, Germany
5 h-index
19 publications
979 citations

Deakin University
Burwood, Australia
4 h-index
8 publications
216 citations
University of Chile
Santiago, Chile
4 h-index
8 publications
240 citations
The University of Texas at Austin
Austin, United States
4 h-index
7 publications
1.3K citations
Tsinghua University
Beijing, China
4 h-index
6 publications
460 citations

University of Central Florida
Orlando, United States
3 h-index
9 publications
286 citations
1–8 of 85
Repository · 4 publications · 55 citations
4
h-index
3 publications · 164 citations
3
h-index
2 publications · 51 citations
2
h-index
Conference · 2 publications · 101 citations
2
h-index
1 publications · 11 citations
1
h-index
1–5