Maxime Wabartha
 |
PhD student, |
About me
I am a 5th year PhD student working on reinforcement learning. I am interested in designing more transparent RL algorithms to improve their interpretability. In addition, I am interested in designing representations for reinforcement learning that can lead to stable and scalable algorithms when used with (non-linear) function approximation. I am also an engineer (MEng from École Centrale de Lille in 2017), and I received my MSc in applied mathematics (master MVA) from Université Paris-Saclay in 2018.
Research
Currently, my research interests include
Transparency and interpretability
Reinforcement learning
Representation learning
Recent Publications
* denotes an equal contribution.
Zaimi, A.*, Wabartha, M.*, Herman, V., Antonsanti, P. L., Perone, C. S., & Cohen-Adad, J. (2018). “AxonDeepSeg: automatic axon and myelin segmentation from microscopy data using convolutional neural networks”. Nature Scientific reports, 8(1), 1-11.
Wabartha, M., Durand, A., Francois-Lavet, V., & Pineau, J. (2020). “Handling Black Swan Events in Deep Learning with Diversely Extrapolated Neural Networks”. International Joint Conference on Artificial Intelligence, 2140-2147.
Wabartha, M. & Pineau, J. (2023). “Piecewise Linear Parametrization of Policies for Interpretable Deep Reinforcement Learning”. NeurIPS Workshop on XAI in Action.
Full list of publications.
A brief cv (last updated: 2023/10/07).
This website was created using Jemdoc.