← Search

Maxime Wabartha

2 accepted papers

2024

Piecewise Linear Parametrization of Policies: Towards Interpretable Deep Reinforcement Learning

ICLR 2024poster

Learning inherently interpretable policies is a central challenge in the path to developing autonomous agents that humans can trust. Linear policies can justify their decisions while interacting in a dynamic environment, but their reduced expressivity prevents them from solving hard tasks. Instead,…

Cited by 4SourcePDFScholar
2020

Handling Black Swan Events in Deep Learning with Diversely Extrapolated Neural Networks

IJCAI 2020poster

By virtue of their expressive power, neural networks (NNs) are well suited to fitting large, complex datasets, yet they are also known to produce similar predictions for points outside the training distribution. As such, they are, like humans, under the influence of the Black Swan theory: models…