Constrained Multi-agent Reinforcement Learning
Constrained Multi-Agent Reinforcement Learning is a formal framework within multi-agent reinforcement learning that extends the standard Markov decision process to concurrent, interacting agents subject to shared constraints on cumulative costs, thereby distinguishing itself by enforcing joint policy optimization under both performance objectives and resource or safety limitations.
16
Publications
658
Citations
40
Authors
18
Institutions
Publications per year
2017–2026
15
Variants
Cmarl
16
Rui Zhao, Yun Li, Fei Gao et al. · IEEE Transactions on Intelligent Transportation Systems · 2023 · 30 citations
1–5 of 16
40
1
h-index
American Institute of Aeronautics and Astronautics, United States
1 publications · 14 citations
1
h-index
1
h-index
1
h-index
1
h-index
1–5 of 40
18
University of Pennsylvania Health System
Philadelphia, United States
1 h-index
2 publications
46 citations
Auburn University
Auburn, United States
1 h-index
1 publications
63 citations
Pusan National University
Busan, South Korea
1 h-index
6 publications
114 citations
Tsinghua University
Beijing, China
1 h-index
2 publications
298 citations
American Institute of Aeronautics and Astronautics
Reston, United States
1 h-index
2 publications
28 citations
Yahoo (United States)
Sunnyvale, United States
1 h-index
1 publications
23 citations
Waseda University
Tokyo, Japan
1 h-index
1 publications
153 citations

University of Waterloo
Waterloo, Canada
1 h-index
5 publications
135 citations
1–8 of 18
2 publications · 90 citations
2
h-index
1 publications · 153 citations
1
h-index
Repository · 1 publications · 16 citations
1
h-index
1 publications · 19 citations
1
h-index
1 publications · 21 citations
1
h-index
1–5