DISA

When? Friday, 23 May, 14-15
Where? Onsite: D2272 at Linnaeus University in Växjö and online
Registration: Please sign up for the PhD-seminar via this link https://forms.gle/SS8cDDJBfRHDQBWZ7 by May 21

Agenda
14.00-14.10 Welcome and practical information from Welf Löwe
14.10-14.55 Distributional Reinforcement Learning – Björn Lindenberg
14.55 – 15.00 Sum up

Abstracts

Distributional Reinforcement Learning – Björn Lindenberg
Distributional Reinforcement Learning (DRL) represents a recent and successful paradigm shift in reinforcement learning, especially for algorithms based on deep learning. Instead of estimating only expected returns, DRL agents learn the full distribution of possible outcomes — offering a richer representation and greater flexibility for algorithm design. This approach has led to improved empirical performance in complex environments and enables new capabilities, such as risk-sensitive behavior. The talk will serve as an introduction to the subject, presenting the theory and possible applications in an accessible way.