报告人:彭滢教授(山东大学)
时间:2022年12月30日周五下午14:00-15:00
腾讯会议ID:482251835
报告题目:Solving Stochastic Optimal Control Problem with Deep Learning Method
报告摘要:
In this talk, we aim to solve the high dimensional stochastic optimal control problem from the view of the stochastic maximum principle via deep learning. By introducing the extended Hamiltonian system which is essentially a Forward Backward Stochastic Differential Equation (FBSDE) with a maximum condition, we reformulate the original control problem as a new one. According to whether the optimal control has an explicit representation, three algorithms are proposed to solve the new control problem. Numerical results for different examples demonstrate the effectiveness of our proposed algorithms, especially in high dimensional cases.
报告人简介:
彭滢现为山东大学中泰证券金融研究院副教授、硕士生导师。2013年获得计算机软件与理论博士学位,2016年由山东大学计算机学院转入中泰证券金融研究院工作。目前主要研究兴趣包括倒向随机微分方程、 随机最优控制及与深度学习、并行计算相结合的交叉研究领域。相关研究成果发表在《Journal of Scientific Computing》、《IEEE Intelligent Systems》、《International Journal of Control》、《Journal of Supercomputing》等人工智能、随机控制、并行计算交叉领域的国际期刊。