Yuhui Wang (王宇辉)

 Ph.D. student, PARNEC Group
Department of Computer Science
Nanjing University of Aeronautics and Astronautics
Supervisor: Prof. Xiaoyang Tan
e-mail: y.wang@nuaa.edu.cn

[This page has been moved to https://wangyuhuix.github.io.]

Biography

 I'm a Ph.D. of Department of Computer Science and Technology in Nanjing University of Aeronautics and Astronautics and a member of PARNEC Group.

 Before my Ph.D. career, I received my M.Sc. degree in Computer Science and Technology in June 2017 from Nanjing University of Aeronautics and Astronautics.

Research Interests

 My research interests include: Reinforcement Learning and Machine Learning. Currently, I'm focused on:

• Fast and sample-efficient reinforcement learning.

• Multi-agent reinforcement learning

• Theory analysis for reinforcement learning

Publications

• Yuhui Wang, Hao He, Xiaoyang Tan, Yaozhong Gan. Trust Region-Guided Proximal Policy Optimization[C]. Proceedings of Advances in Neural Information Processing Systems (NeurIPS), Volume 32., 2019.

• Yuhui Wang, Xiaoyang Tan. Deep Recurrent Belief Propagation Network for POMDPs[C].Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) , 2021, 35(11):10236–10244.

• Yuhui Wang, Hao He, Xiaoyang Tan. Truly Proximal Policy Optimization[C]. Proceedings of Uncertainty in Artificial Intelligence (UAI) , 2019.

• Yuhui Wang, Xiaoyang Tan. Greedy Multi-step Off-Policy Reinforcement Learning [C]. Deep Reinforcement Learning Workshop. Advances in Neural Information Processing Systems. (NeurIPS) , 2020.

• Yuhui Wang, Xin Jin, Xiaoyang Tan. Pornographic Image Recognition by Strongly Supervised Deep Multiple Instance Learning. IEEE International Conference on Image Processing (ICIP), 2016

•  Chao Wen, Xinghu Yao, Yuhui Wang, Xiaoyang Tan. SMIX(λ): Enhancing Centralized Value Functions for Cooperative Multi-Agent Reinforcement Learning[C]. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) , 2020.

•  Xin Jin, Yuhui Wang, Xiaoyang Tan. Pornographic Image Recognition via Weighted Multiple Instance Learning [J]. IEEE Transactions on Cybernetics . 2020.

•  Xinghu Yao, Chao Wen, Yuhui Wang, Xiaoyang Tan. SMIX (𝜆): Enhancing Centralized Value Functions for Cooperative Multi-Agent Reinforcement Learning [J]. IEEE Transactions on Neural Networks and Learning Systems (TNNLS). 2021.

•  Chao Wen, Miao Xu, Zhilin Zhang, Zhenzhe Zheng,Yuhui Wang, et. al. A Cooperative-Competitive Multi-Agent Framework for Auto-bidding in Online Advertising. ACM International Conference on Web Search and Data Mining (WSDM). 2021.

•  Junting Fang, Xiaoyang Tan, Yuhui Wang. ACRM: Attention Cascade R-CNN with Mix-NMS for Metallic Surface Defect Detection. Proceedings of the 25nd International Conference on Pattern Recognition (ICPR). 2020.

Contests & Awards

•  Suzhou Industrial Park Scholarship, 2019

•  NeurIPS Student Travel Grant, 2019

•  UAI Student Travel Grant, 2019

•  The 7th National Information Technology Application Competition, Grand Prize, 2013.

•  The 6th Chinese University Student Computer Design Competition, Second Prize, 2013.

Correspondence

Yuhui Wang, Department of Computer Science and technology

Nanjing University of Aeronautics and Astronautics

Nanjing 211106, China