Title: A control-theoretical perspective of continuous-time reinforcement learning

Speaker: Xin Guo (UC Berkeley)

Time and place: June 23, 13:00 – June 25, 16:00 University of Oslo, Department of Mathematics, Niels Henrik Abels hus, Room 723

Abstract: Reinforcement Learning (RL) is a cornerstone of modern machine learning, enabling agents to learn optimal decision-making through interaction with complex environments and other agents. While RL was traditionally developed for discrete-time settings, many real-world physical and financial systems are intrinsically continuous. This series of lectures provides a comprehensive overview of recent advancements in continuous-time RL, analysed through the rigorous lens of stochastic control theory. It consists of three parts.

See the full announcement for more information, bio, and information about the organisers.