Reward Function Design

Reward Function Design is a methodological construct in reinforcement learning that specifies the formal process of defining a scalar feedback signal to guide agent behavior by encoding task objectives and desired outcomes within a learning environment.

861

Publications

38.5K

Citations

2.8K

Authors

753

Institutions

Publications per year

2017–2026

747

Parents

Reward Design

Publications

861

DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning

Wenhan Xiong, Thien Hoang, William Yang Wang · 2017 · 772 citations · Full text

Computing, Computer Science, Knowledge Representation +16

Emergence of Locomotion Behaviours in Rich Environments

Nicolas Heess, Dhruva Tb, Sriram Srinivasan et al. · arXiv (Cornell University) · 2017 · 669 citations · Full text

Engineering, Autonomous Systems, Computer Science +17

Deep Reinforcement Learning for Unsupervised Video Summarization With Diversity-Representativeness Reward

Kaiyang Zhou, Yu Qiao, Tao Xiang · Proceedings of the AAAI Conference on Artificial Intelligence · 2018 · 469 citations · Full text

Computing, Computer Science, Computer Vision +12

Large-Scale Study of Curiosity-Driven Learning

Yuri Burda, Harri Edwards, Deepak Pathak et al. · arXiv (Cornell University) · 2018 · 367 citations · Full text

Computing, Autonomous Systems, Computer Science +17

PressLight

Hua Wei, Chacha Chen, Guanjie Zheng et al. · 2019 · 364 citations · Full text

Engineering, Transportation Planning, Machine Learning +16

1–5 of 861

Authors

2.8K

SL
Sergey Levine
University of California, Berkeley, United States
15 publications · 650 citations
12
h-index
SS
Satinder Singh
University of Michigan, United States
7 publications · 263 citations
7
h-index
RL
Richard L. Lewis
University of Michigan, United States
7 publications · 244 citations
7
h-index
CF
Chelsea Finn
University of California, Berkeley, United States
6 publications · 185 citations
6
h-index
SN
Scott Niekum
The University of Texas at Austin, United States
5 publications · 162 citations
5
h-index

1–5 of 2.8K

Institutions

753

1–8 of 753

Venues

arXiv (Cornell University)
Repository · 77 publications · 3.9K citations
32
h-index
IEEE Access
31 publications · 1.3K citations
23
h-index
IEEE Transactions on Vehicular Technology
17 publications · 1.2K citations
17
h-index
Proceedings of the AAAI Conference on Artificial Intelligence
Conference · 17 publications · 1K citations
15
h-index
Sensors
19 publications · 385 citations
15
h-index

1–5