Multi-agent Reinforcement Learning
Multi-Agent Reinforcement Learning is a subfield of reinforcement learning in which multiple autonomous agents learn optimal decision-making policies through interaction with a shared environment and with one another, distinguished from single-agent reinforcement learning by the inclusion of inter-agent dynamics such as cooperation, competition, or negotiation.
2K
Publications
127.1K
Citations
5.9K
Authors
1.3K
Institutions
Publications per year
2017–2026
1.6K
2K
Grandmaster level in StarCraft II using multi-agent reinforcement learning
Oriol Vinyals, I. Babuschkin, Wojciech Marian Czarnecki et al. · Nature · 2019 · 3.4K citations
1–5 of 2K
5.9K
21
h-index
21
h-index
19
h-index
18
h-index
17
h-index
1–5 of 5.9K
1.3K
Nanyang Technological University
Singapore, Singapore
36 h-index
108 publications
7.4K citations
Tsinghua University
Beijing, China
36 h-index
175 publications
12.2K citations

University of Electronic Science and Technology of China
Chengdu, China
33 h-index
131 publications
10.9K citations

Beijing University of Posts and Telecommunications
Beijing, China
29 h-index
138 publications
6.6K citations

Imperial College London
London, United Kingdom
28 h-index
78 publications
5.3K citations

Shanghai Jiao Tong University
Shanghai, China
26 h-index
108 publications
7.5K citations

Southeast University
Nanjing, China
24 h-index
95 publications
4.7K citations

National University of Defense Technology
Changsha, China
23 h-index
99 publications
6.6K citations
1–8 of 1.3K
Repository · 243 publications · 15.4K citations
54
h-index
64 publications · 5.3K citations
41
h-index
45 publications · 4.2K citations
34
h-index
38 publications · 2.8K citations
31
h-index
52 publications · 3.1K citations
28
h-index
1–5