Batch Reinforcement Learning
Batch Reinforcement Learning is a reinforcement learning paradigm in which the agent learns a policy exclusively from a fixed dataset of previously collected interactions, without further environment exploration.
153
Publications
11.1K
Citations
475
Authors
150
Institutions
Publications per year
2017–2026
94
153
Dota 2 with Large Scale Deep Reinforcement Learning
Christopher Berner, Greg Brockman, Brooke Chan et al. · arXiv (Cornell University) · 2019 · 1K citations · Full text
Tree-Based Batch Mode Reinforcement Learning
Damien Ernst, Pierre Geurts, Louis Wehenkel · 2005 · 866 citations · Full text
Léon Bottou, Y. Le Cun · 2003 · 337 citations
1–5 of 153
475
9
h-index
7
h-index
7
h-index
6
h-index
5
h-index
1–5 of 475
150
KU Leuven
Leuven, Belgium
9 h-index
24 publications
2.8K citations
University of Illinois Urbana-Champaign
Urbana, United States
7 h-index
13 publications
829 citations
University of Liège
Liège, Belgium
6 h-index
10 publications
3.1K citations
Flemish Institute for Technological Research
Mol, Belgium
6 h-index
7 publications
946 citations
Politecnico di Milano
Milan, Italy
6 h-index
20 publications
1K citations
Google (United States)
Mountain View, United States
5 h-index
35 publications
1.7K citations

McGill University
Montreal, Canada
5 h-index
8 publications
877 citations

Supélec
Gif-sur-Yvette, France
4 h-index
8 publications
507 citations
1–8 of 150
Repository · 43 publications · 3.1K citations
23
h-index
6 publications · 580 citations
6
h-index
4 publications · 319 citations
4
h-index
4 publications · 721 citations
4
h-index
JMLR · 3 publications · 276 citations
3
h-index
1–5