default author photo

Yasen Cui

Hefei University of Technology

193 Tunxi Rd

Baohe

Hefei

China

  • Hefei University of Technology

SCHOLARLY PAPERS

1

DOWNLOADS

56

TOTAL CITATIONS

0

Scholarly Papers (1)

Actions:
Email selected abstracts
1.

Rkl: Reward-Kullback-Leibler Divergence Method for Improving Machine Learning Model Prediction Performance

Number of pages: 22 Posted: 07 Nov 2023
Jian Zhu, Yasen Cui, Wei Zhou, Huaijuan Zang, Haiyan Zhang, Yongsheng Ren, Jiajia Xu, Shu Zhan and Wenhui Ma
Hefei University of Technology, Hefei University of Technology, affiliation not provided to SSRN, Hefei University of Technology, Hefei University of Technology, Kunming University of Science and Technology, affiliation not provided to SSRN, Hefei University of Technology and Kunming University of Science and Technology - The National Engineering Laboratory for Vacuum Metallurgy
Downloads 56 (1,000,027)

Abstract:

Loading...

Machine Learning, Graph Neural Networks, Materials Performance Prediction, KL Divergence, Reward Functions, Reinforcement Learning from Human Feedback