Decentralized Policy Learning is a multi-agent reinforcement learning framework in which each agent independently learns a policy using locally available information, without access to a centralized controller or global state, thereby distinguishing it from centralized or shared policy approaches through its reliance on autonomous decision-making and local observability.
131
Publications
9.3K
Citations
378
Authors
155
Institutions
Publications per year
2017–2026
98
Parents
Publications
131
Counterfactual Multi-Agent Policy Gradients
Jakob Foerster, Gregory Farquhar, Triantafyllos Afouras et al. · arXiv (Cornell University) · 2017 · 478 citations · Full text
1–5 of 131
Authors
378
- GF
7
h-index
- SW
6
h-index
- CA
5
h-index
- GY
4
h-index
- DN
4
h-index
1–5 of 378
Institutions
155
Nanyang Technological University
Singapore, Singapore
5 h-index
11 publications
574 citations
Georgia Institute of Technology
Atlanta, United States
4 h-index
10 publications
3.1K citations
University of Southern California
Los Angeles, United States
4 h-index
8 publications
490 citations
University of Oxford
Oxford, United Kingdom
4 h-index
19 publications
11K citations
Imperial College London
London, United Kingdom
4 h-index
5 publications
399 citations
Peking University
Beijing, China
3 h-index
11 publications
737 citations
Princeton University
Princeton, United States
3 h-index
3 publications
200 citations
University of California, Santa Cruz
Santa Cruz, United States
3 h-index
6 publications
104 citations
1–8 of 155
Venues
- arXiv (Cornell University)
Repository · 31 publications · 2.3K citations
18
h-index
- IEEE Access
3 publications · 120 citations
3
h-index
- Neurocomputing
3 publications · 137 citations
3
h-index
- Transportation Research Part C Emerging Technologies
3 publications · 178 citations
3
h-index
- IEEE/ACM Transactions on Networking
TON · 2 publications · 84 citations
2
h-index
1–5