Policy Distillation
Policy Distillation is a policy learning method that transfers knowledge from a high-capacity teacher policy to a more compact student policy by minimizing the divergence between their action distributions across states, enabling efficient deployment in data-constrained robotic environments.
22
Publications
1.2K
Citations
140
Authors
32
Institutions
Publications per year
2017–2026
20
22
A Deep Hierarchical Approach to Lifelong Learning in Minecraft
Chen Tessler, Shahar Givony, Tom Zahavy et al. · arXiv (Cornell University) · 2016 · 142 citations · Full text
Andrei A. Rusu, Sergio Gómez Colmenarejo, Çağlar Gülçehre et al. · arXiv (Cornell University) · 2015 · 87 citations · Full text
1–5 of 22
140
2
h-index
2
h-index
2
h-index
2
h-index
2
h-index
1–5 of 140
32
Google (United States)
Mountain View, United States
2 h-index
11 publications
861 citations
Samsung (South Korea)
Seoul, South Korea
2 h-index
2 publications
63 citations
Google DeepMind (United Kingdom)
London, United Kingdom
2 h-index
14 publications
978 citations

University of Oulu
Oulu, Finland
1 h-index
1 publications
30 citations

Beijing University of Posts and Telecommunications
Beijing, China
1 h-index
2 publications
60 citations

The University of Western Australia
Perth, Australia
1 h-index
1 publications
43 citations
Arizona State University
Tempe, United States
1 h-index
1 publications
30 citations
University of California, Irvine
Irvine, United States
1 h-index
5 publications
95 citations
1–8 of 32
Repository · 12 publications · 548 citations
12
h-index
Conference · 3 publications · 371 citations
3
h-index
1 publications · 30 citations
1
h-index
1 publications · 33 citations
1
h-index
TON · 1 publications · 30 citations
1
h-index
1–5