Title: Usage of Bayesian neural network in deep reinforcement learning
Authors: Leo Grill - Universite de Poitiers (France) [presenting]
Yousri Slaoui - University of Poitiers (France)
David Nortershauser - Orange (France)
Stephane Le Masson - Orange (France)
Abstract: While reinforcement learning finds applications in various domains, the Bayesian methods have special attention, especially deep learning. They can be used to deal with issues such as overfitting or explainable modeling. We developed the usage of using a Bayesian neural network as an actor in the actor-critic algorithms. We show the benefits of using these methods in deep-reinforcement learning.