Sparse Reward Design
Sparse Reward Design is a reward engineering methodology in reinforcement learning wherein the reward signal is deliberately structured to be provided only at sparse intervals or upon achievement of specific milestones, distinguishing it from dense reward designs by its minimal and infrequent feedback to guide agent learning.
43
Publications
1.4K
Citations
201
Authors
74
Institutions
Publications per year
2017–2026
42
Parents
43
Learning Loop Invariants for Program Verification
Xujie Si, Hanjun Dai, Mukund Raghothaman et al. · Neural Information Processing Systems · 2018 · 55 citations
1–5 of 43
201
2
h-index
2
h-index
2
h-index
2
h-index
2
h-index
1–5 of 201
74
Tsinghua University
Beijing, China
4 h-index
13 publications
267 citations
University of Science and Technology of China
Hefei, China
3 h-index
3 publications
83 citations

Imperial College London
London, United Kingdom
2 h-index
5 publications
422 citations
Shandong University
Jinan, China
2 h-index
9 publications
310 citations

Northwestern Polytechnical University
Xi'an, China
2 h-index
2 publications
88 citations
Nanyang Technological University
Singapore, Singapore
2 h-index
2 publications
66 citations

Nanjing University of Aeronautics and Astronautics
Nanjing, China
2 h-index
8 publications
408 citations

Hong Kong Polytechnic University
Hong Kong, Hong Kong
2 h-index
3 publications
127 citations
1–8 of 74
Repository · 9 publications · 285 citations
9
h-index
3 publications · 190 citations
3
h-index
Conference · 3 publications · 74 citations
3
h-index
2 publications · 62 citations
2
h-index
2 publications · 93 citations
2
h-index
1–5