Hey, I'm Théo Jaunet

I'm a Ph.D. student at LIRIS lab, INSA-Lyon (France) since september 2018, where I'm advised by Romain Vuillemot and Christian wolf. My research is funded for 3 years by a French ministry Ph.D. fellowship and supported by the M2I project.


Memory Reduction

We built Doom player AI using Deep Reinforcement learning. While playing, it builds and updates an inner representation (memory) of the game, its environment. Reducing...

VISXAI 2019 — Theo Jaunet, Romain Vuillemot, Christian Wolf — Best Submission Prize


A visual analytics interface to interpret the internal memory of an agent (e.g. a robot) trained using deep reinforcement learning.

Research Report — Theo Jaunet, Romain Vuillemot, Christian Wolf