High-dimensional State Spaces
High-Dimensional State Spaces is a state space in reinforcement learning characterized by a large number of state variables or features, which distinguishes it from low-dimensional state spaces by exacerbating computational and sampling challenges in value function approximation and policy optimization.
856
Publications
53.3K
Citations
2.3K
Authors
687
Institutions
Publications per year
2017–2026
353
Parents
856
Deterministic policy gradient algorithms
David Silver, Guy Lever, Nicolas Heess et al. · HAL (Le Centre pour la Communication Scientifique Directe) · 2014 · 1.7K citations · Full text
Articulated body motion capture by annealed particle filtering
J. Deutscher, A. Blake, Ian Reid · 2002 · 862 citations
Curiosity-Driven Exploration by Self-Supervised Prediction
Deepak Pathak, Pulkit Agrawal, Alexei A. Efros et al. · 2017 · 688 citations · Full text
1–5 of 856
2.3K
10
h-index
9
h-index
9
h-index
Massachusetts Institute of Technology, United States
8 publications · 407 citations
8
h-index
7
h-index
1–5 of 2.3K
687
Carnegie Mellon University
Pittsburgh, United States
24 h-index
55 publications
4K citations
Stanford University
Stanford, United States
18 h-index
58 publications
7.4K citations
Massachusetts Institute of Technology
Cambridge, United States
18 h-index
45 publications
4K citations
University of California, Berkeley
Berkeley, United States
16 h-index
50 publications
8K citations
Google (United States)
Mountain View, United States
14 h-index
69 publications
3K citations
Georgia Institute of Technology
Atlanta, United States
13 h-index
27 publications
1.1K citations
Tsinghua University
Beijing, China
13 h-index
31 publications
1K citations
University of Washington
Seattle, United States
12 h-index
31 publications
1.8K citations
1–8 of 687
Repository · 129 publications · 5.9K citations
38
h-index
Conference · 12 publications · 639 citations
11
h-index
9 publications · 473 citations
9
h-index
8 publications · 612 citations
8
h-index
IJRR · 7 publications · 4K citations
7
h-index
1–5