Multiobjective Reinforcement Learning
Multiobjective Reinforcement Learning is a reinforcement learning framework that extends the standard Markov decision process to environments with multiple, often competing, objective functions, where the goal is to learn policies that optimize a vector of cumulative rewards rather than a scalar return.
82
Publications
5.2K
Citations
256
Authors
107
Institutions
Publications per year
2017–2026
61
Variants
Morl
Parents
82
Empirical evaluation methods for multiobjective reinforcement learning algorithms
Peter Vamplew, Richard Dazeley, Adam Berry et al. · Machine Learning · 2010 · 274 citations · Full text
1–5 of 82
256
9
h-index
8
h-index
7
h-index
5
h-index
4
h-index
1–5 of 256
107
Vrije Universiteit Brussel
Brussels, Belgium
8 h-index
18 publications
3.3K citations

Federation University
Ballarat, Australia
8 h-index
20 publications
1.9K citations

Deakin University
Burwood, Australia
5 h-index
9 publications
1.1K citations
Politecnico di Milano
Milan, Italy
4 h-index
10 publications
858 citations
University of Oxford
Oxford, United Kingdom
4 h-index
9 publications
499 citations
Google (United States)
Mountain View, United States
3 h-index
4 publications
102 citations

National University of Defense Technology
Changsha, China
3 h-index
12 publications
2.2K citations

Ollscoil na Gaillimhe – University of Galway
Galway, Ireland
3 h-index
10 publications
1.3K citations
1–8 of 107
Repository · 7 publications · 318 citations
7
h-index
5 publications · 184 citations
5
h-index
4 publications · 392 citations
4
h-index
3 publications · 104 citations
3
h-index
3 publications · 75 citations
3
h-index
1–5