Report title: calculating equipment mean variance strategy with reinforcement learning

Reported by: Dong Yuchao

Report time: 10:00-11:00, December 27, 2019 (Friday)

Place of report: conference room 212, College of Science

In this talk, we consider the mean variance problem for terminal log return under incomplete market. In additional, an entry term is included in the objective functional to enhance exploration of the strategy. As the problem is time-dependent, we characterize the equilibrium strategy with the help of extended HJB equation. Finally, we propose a learning process to obtain the strategy through the interaction with the market.

Professor profile: Yuchao Dong received Ph.D degree in 2016 from school of Mathematical Science, Fudan University. Now he is a research fellow in the Department of mathematics, NUS. His major research interest includes mathematical finance and stoic optimal control theory