My motivation for doing my job, and before that, being a student and aiming at becoming a researcher, is mostly a search for understanding things, and think about things. And sharing this with other people, colleagues, students, whoever might be interested in, together going further towards new unknown territories.
I am not really interested in digging further, rather in finding new areas to dig into. I prefer exploring new areas, rather than exploiting.
This led me to change my field of interest very strongy along the years and visit various remote areas of computer science: symbolic AI, computer architecture, languages and compilers, genetic algorithms, combinatorial optimization, multi-agent systems, machine learning, data mining, numerical/statistical AI.
This also led me to work with researchers of other fields: marine biologists, behaviorist psychologists, agronomists, health researchers.
This also led me to collaborate with companies on various topics to understand companies point of view, needs, etc.
In this section, I describe my current research activities and projects.
Fundamentally, my research domain is machine learning, and particularly sequential decision making under unceertainty, mostly reinforcement learning, a bit of bandits, and a bit of any other relevant topic.
I have decided a couple of years ago to focus on a set of research topics and applications of my research. After 30 years of research activities, I feel like I need to try to make my research useful, at least to some extent, to the well-being of society, humankind, and Life on earth (!). This led me to select the set of research questions I want to investigate in the coming years. Regarding applications, I want to focus on health, and sustainable development.
I think that machine learning has brought new tools, algorithms, methods, ... that have to be used, put to the test, and tailored to important fields of applications. Applications also bring questions and challenges that have to be dealt with by fundamental research, and drawing my attention to issues that are meaningfull.
In this section, I say a few words about the directions in which I work.
To summarize my opinion about so-called AI, there is absolutely nothing intelligent in it: current AI systems, sometimes achieving remarkable feats, are completely stupid, and rely exclusively on computation power, and the smartness of their designers and implementors. I want to go further than that. There are numerous tasks where current state-of-the-art AI is simply unable to do anyhting or, if it can, does it in a completely stupid way, a completely different way from the one we, as human beings, use. You may check this page where I try to gather my thinking about AI (sorry this page is written in French for the moment).
An other mysterious word in my research is "learning". Like "intelligence", algorithms do not learn anything in the way human beings or animals learn. In machine learning, learning means computing a set of parameters. Nothing else.
Many papers in top conferences and journal (and others, less top) claim they achieve state-of-the-art performance on this or that RL tasks. Very often (almost always), it is totally impossible to redo their experiments at all, and when this is possible, obtain the same results and their state-of-the-art-'ness.
One may blame the authors. Very often, athors do not really bother about that issue, they just want to have their paper accepted, hence needing to be state-of-the-art. However, when we dig further, we realize that even with the best will and making efforts, obtaining reproducible experimental results in reinfrocement learning is difficult. There are many reasons for that. With some of my colleagues in Scool, we have been working for many years now on this issue, trying to find real solutions that can be used in practice. There are statistical problems, and computer science problems. Adequate statistical tools are needed to assess whether an algorithm performs better than an other (see our paper on the adastop test). The investigation of computer science problems is on-going, an early report after them having been issued in June 2026 (see this research report).
I am working with Prof. F. Pattou and his INSERM Unit 1190 at the University de Lille and CHU de Lille.
Together, we explore how machine learning, reinforcement learning and bandits, may improve health-care, particularly post-surgery patient follow-up.
This collaboration is funded by a set of projects, including this i-site ULNE Bandits for Health (B4H) project. We have designed and set-up a web service to predict weight evolution of obese patients undergoing bariatric surgery. In Sep 2022, Inria published an article on Inria website regarding the Bandits for Health (B4H) project. In 2023, this collaboration will go on much further, funded by the ANR BIP-UP (2023-2026).
In Scool, J. Teigny has worked and T. Soumphonphakdy is working with me as engineers, Patrick Saux is doing his PhD on post-surgery patient follow-up.
I also had (2019-2022) a collaboration with P. Schegg, PhD student in the Defrost team and the Robocath company, on the control by reinforcement learning of catheters used in surgery. The work on the control of soft robots with reinforcement learning goes on through my collaboration with Defrost.
I have, or had, activities on the following topics related to sustainable development:
In this section, I very briefly describe the topics I worked on in the past.