Yixuan Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yixuan Wang has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
Feng Liu
Department of Nephrology, China-Japan Union Hospital of Jilin University, Changchun, China
1 shared publication- Hongjun Li
China-Japan Union Hospital of Jilin University, No. 126 Xiantai Street, Changchun, 130033, Jilin, China.
1 shared publication Lihua Guo
Department of Nephrology, China-Japan Union Hospital of Jilin University, Changchun, China
1 shared publicationQi Jiang
Department of Nephrology, China-Japan Union Hospital of Jilin University, Changchun, China
1 shared publication
Latest Publications
- 11 November 2022
- Published by SPIE-Intl Soc Optical Eng
- Vol. 12348, 19-283
Wasserstein gradient flows policy optimization via input convex neural networks
Reinforcement learning (RL) is a widely used learning paradigm today. As a common RL method, policy optimization usually updates parameters by maximizing the expected cumulative rewards and other information obtained in the process of environment interaction. To get a better understanding of the RL and its learning theory, there is also proposed that RL can be regarded as the optimal transport problem in a probability measure space. On this basis, we get a large-scale Wasserstein gradient flow RL method by introducing input convex neural networks (ICNNs) to improve the Jordan-Kinderlehrer-otto (JKO) scheme.
- 11 November 2022
- Published by SPIE-Intl Soc Optical Eng
- Vol. 12348, 19-283
Wasserstein gradient flows policy optimization via input convex neural networks
Reinforcement learning (RL) is a widely used learning paradigm today. As a common RL method, policy optimization usually updates parameters by maximizing the expected cumulative rewards and other information obtained in the process of environment interaction. To get a better understanding of the RL and its learning theory, there is also proposed that RL can be regarded as the optimal transport problem in a probability measure space. On this basis, we get a large-scale Wasserstein gradient flow RL method by introducing input convex neural networks (ICNNs) to improve the Jordan-Kinderlehrer-otto (JKO) scheme.
- Open Access
- 17 June 2019
- Published by Royal Society of Chemistry (RSC) in RSC Advances
- Vol. 9 (33) , 18815-18822
A cobalt-doped iron oxide nanozyme as a highly active peroxidase for renal tumor catalytic therapy
Cobalt dopant in Fe3O4 nanozymes improved their binding affinity to H2O2 and enhanced the tumor catalytic therapy efficacy.
- 17 June 2019
- Published by Royal Society of Chemistry (RSC) in RSC Advances
- Vol. 9 (33) , 18815-18822
Open AccessA cobalt-doped iron oxide nanozyme as a highly active peroxidase for renal tumor catalytic therapy
Cobalt dopant in Fe3O4 nanozymes improved their binding affinity to H2O2 and enhanced the tumor catalytic therapy efficacy.