Mathematical Finance & Financial Data Science Seminar
SciPhy RL: Distributional Offline Continuous-Time Reinforcement Learning with Neural Physics-Informed PDEs
Speaker: Igor Halperin, VP of AI Asset Management, Fidelity Investments
Location: Online Zoom access provided to registrants
Date: Tuesday, November 16, 2021, 5:30 p.m.
This talk addresses distributional offline continuous-time reinforcement learning (DOCTR-L) approach to problems of high-dimensional optimal control. A soft distributional version of the classical Hamilton-Jacobi-Bellman (HJB) equation is given by a semilinear partial differential equation (PDE), aka `the soft HJB equation’. SciPhy RL uses Neural PDEs and Physics-Informed Neural Networks (PINNs) developed in the field of Scientific Machine Learning (SciML) to directly learn (solve) the soft HJB equation from offline data, without assuming that the latter correspond to a previous optimal or near-optimal policy. The SciPhy RL method thus reduces DOCTR-L to solving neural PDEs from data. Our algorithm called Deep DOCTR-L converts offline high-dimensional data into an optimal policy in one step by reducing it to supervised learning, instead of relying on value iteration or policy iteration methods. The method enables a computable approach to the quality control of obtained policies in terms of both expected returns and uncertainties about their values.
Igor Halperin is an AI Research Associate at Fidelity Investments. His research focuses on using methods of reinforcement learning, information theory, and physics for financial problems such as portfolio optimization, dynamic risk management, and inference of sequential decision-making processes of financial agents. Igor has an extensive industrial and academic experience in statistical and financial modeling, in particular in the areas of option pricing, credit portfolio risk modeling, and portfolio optimization. Prior to joining Fidelity, Igor worked as a Research Professor of Financial Machine Learning at NYU Tandon School of Engineering. Before that, Igor was an Executive Director of Quantitative Research at JPMorgan, and a quantitative researcher at Bloomberg LP. Igor has published numerous articles in finance and physics journals, and is a frequent speaker at financial conferences. He has co-authored the books “Machine Learning in Finance: From Theory to Practice” (Springer 2020) and “Credit Risk Frontiers” (Bloomberg LP, 2012). Igor has a Ph.D. in theoretical high energy physics from Tel Aviv University, and a M.Sc. in nuclear physics from St. Petersburg State Technical University.
This event is free, but requires registration. Please click here to register