Multi-task Reinforcement Learning
Multi-Task Reinforcement Learning is a reinforcement learning paradigm that enables a single agent to simultaneously learn multiple distinct tasks by sharing knowledge across them through a common policy or value function, thereby improving generalization and sample efficiency compared to learning each task independently.
130
Publications
8.3K
Citations
451
Authors
147
Institutions
Publications per year
2017–2026
106
Variants
Mtrl
Parents
130
An overview of multi-task learning
Yu Zhang, Qiang Yang · National Science Review · 2017 · 1.1K citations · Full text
Experience Replay for Continual Learning
David Rolnick, Arun Ahuja, Jonathan Schwarz et al. · arXiv (Cornell University) · 2018 · 376 citations · Full text
Multi-task reinforcement learning
Aaron Wilson, Alan Fern, Soumya Ray et al. · 2007 · 272 citations
1–5 of 130
451
5
h-index
4
h-index
3
h-index
3
h-index
3
h-index
1–5 of 451
147
Google DeepMind (United Kingdom)
London, United Kingdom
8 h-index
51 publications
4.5K citations
Google (United States)
Mountain View, United States
7 h-index
30 publications
9.2K citations
Carnegie Mellon University
Pittsburgh, United States
6 h-index
8 publications
296 citations

Chinese Academy of Sciences
Beijing, China
5 h-index
3 publications
78 citations
Tsinghua University
Beijing, China
5 h-index
5 publications
219 citations
Nanyang Technological University
Singapore, Singapore
4 h-index
5 publications
387 citations
University of Chinese Academy of Sciences
Beijing, China
4 h-index
3 publications
78 citations
University of California, Berkeley
Berkeley, United States
4 h-index
8 publications
811 citations
1–8 of 147
Repository · 35 publications · 2.8K citations
23
h-index
Conference · 5 publications · 412 citations
6
h-index
2 publications · 106 citations
3
h-index
3 publications · 48 citations
3
h-index
1 publications · 26 citations
3
h-index
1–5