I am a second year PhD student supervised by Riad Akrour and Philippe Preux.

I study Interpretable Reinforcement Learning. Interpretable Reinforcement Learning can be achieved through the learning of human readable policies such as Decision Tree Policies. And/or by defining learned policies over a space of Semantically meaningful states by using Representations Learning such as oject instead of pixels.

I aspire to become a University Professor and I am looking to extend my network and collaborations so don't hesitate to reach out to me.

Hector Kohler

hector dot kohler at inria.fr

Inria Scool
Université de Lille
Villeneuve d'Ascq
France

Open Source

  • I contribute to rlberry. It is an open source Reinforcement Learning library aimed at education and research. Rlberry main strength is its AgentManager class used to automatise statistically meaningful evaluations of RL agents.
    RLberry Github
Plain Academic