Action Space Formulation
Action Space Formulation is a dynamic programming construct that specifies the set of permissible decisions or operations at each state, distinguishing itself by formally defining the feasible actions available to an agent in sequential decision-making processes.
762
Publications
37.8K
Citations
2.5K
Authors
654
Institutions
Publications per year
2017–2026
530
Parents
762
StarCraft II: A New Challenge for Reinforcement Learning
Oriol Vinyals, Timo Ewalds, Sergey Bartunov et al. · arXiv (Cornell University) · 2017 · 685 citations · Full text
A Theoretical Framework for Conversational Search
Filip Radlinski, Nick Craswell · 2017 · 430 citations
Multiagent Planning with Factored MDPs
Carlos Guestrin, Daphne Koller, Ronald Parr · 2001 · 403 citations
1–5 of 762
2.5K
7
h-index
5
h-index
5
h-index
5
h-index
5
h-index
1–5 of 2.5K
654

Beijing University of Posts and Telecommunications
Beijing, China
19 h-index
65 publications
4.3K citations
Tsinghua University
Beijing, China
19 h-index
80 publications
4K citations
Carnegie Mellon University
Pittsburgh, United States
17 h-index
34 publications
1.6K citations
Nanyang Technological University
Singapore, Singapore
16 h-index
31 publications
1.7K citations

Southeast University
Nanjing, China
13 h-index
36 publications
2K citations
University of California, Berkeley
Berkeley, United States
13 h-index
40 publications
3.5K citations

Beijing Institute of Technology
Beijing, China
11 h-index
31 publications
2.5K citations

Shanghai Jiao Tong University
Shanghai, China
11 h-index
39 publications
1.8K citations
1–8 of 654
Repository · 100 publications · 4.5K citations
32
h-index
17 publications · 1.2K citations
16
h-index
17 publications · 745 citations
16
h-index
Conference · 19 publications · 614 citations
15
h-index
12 publications · 1.1K citations
12
h-index
1–5