Risk-Aware Reinforcement Learning for Finance
Abstract
Reinforcement learning (RL) is a model agnostic approach for “learning” optimal strategies where an agent is faced with maximizing or minimizing an objective functional over a class of strategies that are, in general, stochastic processes. Traditionally, in RL, the objective functionals are expectations of total running rewards/costs – and ignores risks. In this talk, I will provide an overview of some new approaches to pose and solve time consistent versions of risk-aware RL problems with applications to financial modeling. Based on various joint works with Alvaro Cartea, Anthony Coache, Silvana Pesenti, Yuri Saporito, Rodrigo Targino, Hariam Tatsat, and Ye Sheng Wang.
Watch recording ↗About the speaker
Sebastian Jaimungal is a full professor of mathematical finance in the Department of Statistical Sciences. He is an elected SIAM fellow, an elected fellow of the Fields Institute for Mathematical Sciences, and a member of the Oxford-Man Institute. Furthermore, he is the former Chair for the SIAM activity group in Financial Mathematics and Engineering (SIAG/FM&E), and an Associate Editor for Quantitative Finance, ASA Journal Data Science in Sciece, Journal of Dynamics and Games, Frontiers of Mathematical Finance, , the International Journal of Theoretical and Applied Finance (IJTAF), and Journal of Risks. He was a founding board member of the Commodities and Energy Markets Association and now serves on its advisory board. His research interests span stochastic control and games, reinforcement learning, machine learning, clean energy, and algorithmic trading.