Offline Multi-objective Reinforcement Learning
Offline Multi-Objective Reinforcement Learning is a reinforcement learning framework in which an agent learns a policy that optimally balances multiple competing objectives using a fixed, previously collected dataset of interactions, without further environment exploration.
5
Publications
141
Citations
25
Authors
9
Institutions
Publications per year
2017–2026
5
5
Chien-Wei Fu, Meng‐Lin Ku, Yu‐Jia Chen et al. · IEEE Internet of Things Journal · 2023 · 25 citations
1–5 of 5
25
1
h-index
1
h-index
1
h-index
1
h-index
1
h-index
1–5 of 25
9
National Central University
Taoyuan City, Taiwan
1 h-index
3 publications
75 citations
Tsinghua University
Beijing, China
1 h-index
5 publications
105 citations
Fraunhofer Institute for Software and Systems Engineering
Dortmund, Germany
1 h-index
1 publications
40 citations

Paderborn University
Paderborn, Germany
1 h-index
5 publications
200 citations
Ministry of Public Security of the People's Republic of China
Beijing, China
1 h-index
3 publications
81 citations
Singapore University of Technology and Design
Singapore, Singapore
1 h-index
1 publications
25 citations
Lockheed Martin (United States)
Bethesda, United States
1 h-index
2 publications
56 citations

Northeastern University
Shenyang, China
1 h-index
6 publications
162 citations
1–8 of 9
1 publications · 25 citations
1
h-index
1 publications · 27 citations
1
h-index
TNSM · 1 publications · 40 citations
1
h-index
TON · 1 publications · 21 citations
1
h-index
1–4