Odalric-Ambrym Maillard

Vision

I am a researcher in reinforcement learning, a great field of research at the crossing of Mathematical Statistics and Computer Science. I am generally a theory guy. But I also believe it is important to promote application of reinforcement learning that are not only scientifically exciting and can have a great potential for the world. In my early years as a young researcher, I could see a lot of academic work about multi-armed bandit and reinforcement learning was motivated my application from the web-industry. Multi-armed bandit theory attracted tremendous interest from the e-market industry (especially recommender systems for ad-placement strategies), to the point it often biased resarch questions. Soon the design of optimal ad placement strategies became the standard application example in academic conferences. As many researchers I was somehow curioous that theoretical work is used in some real-usecase. However, I was also reluctant to see the ethically gray approch from the industry, knowing that the very same tools can be used to develop applications with a much higher societal value, and also give rise to a huge avenue of exciting scientific challenges. As a theoretician, I could have easily ignored this. But from an ethical standpoint, I could not stand that most of our research is eventually applied in such an unethical way.

"As academic researchers, it is our duty to open novel application paths, choose which future we want to create, and picture the world we dream of beyond the existing applications of current research."

Over the next years, I became deeply convinced that as academic researchers, it is our duty to open novel application paths. More precisely, it is our duty to choose which future we want to create, and picture the world we dream of beyond the existing applications of current research. This means, rather than following the current industry trend, we, academic researchers, should design the societal applications that currently do not exist but will benefit the society in the future.

A diversity of agrosystems that could benefit from agroecology principles.

From 2018, I actively considered Agroecology as an alternative application area for recommender systems with tremendous opportunities for research questions and society. Indeed, moving from Agriculture to Agroecology requires considering novel objectives beyond yield/profit, togegher with a large diversity of variables of interest beyond climate and soil. This in turns calls for massive experimentation, as existing simulators fail to accurately model the complex dynamics of all the entities at stake. That is, we need massive on-field experimentation, to try and test hypotheses in large range of contexts. This is where sequential decision making, adaptive design of experiments can play a major role, offering algorithms able to automatically adapt to the data, reducing risk and length of experiments. Experimentation in Agroecology resembles experimentation in clinical trials (after all, applying a technical itinerary can be seen as a medical treatment), but the data is usually less sensitive and also at a larger scale, which makes the field especially suitable for such application. But the data acquisition infrastructures must be coordinated for the data to be accessible and useful.

"The more applied you go, the stronger theory you need."

And of course, applying reinforcement learning to Agorecology requires solving a number of exciting mathematical challenges that may apply much beyond this field, to all experimental sciences at large. As I often say: "The more applied you go, the stronger theory you need." And we definitely need to build stronger theory for agrosystems. For instance, classical distribution of rewards should be considered non-parametric, the objectiev is often risk-averse rather than risk-neutral, we do not act purely sequentially but rather group-sequentially and from a contextual perspective, which yields study of contextual variants of hypothesis testing or reinforcement learning oif thrilling mathematical interest.

Philosophy

We have little opportunity, in the academic world, to express one’s feelings, philosophy of life, or enthousiasm about knowledge. We communicate only via research articles and are reduced to disambodied metrics that convey only a partial aspect of what we are. I believe this is sad and counter-productive. As every creative person, we, researchers, have a rich and complex personality that takes time to understand and appreciate.
Let me just give you a glimpse about me, the guy behind the articles, through the following hopefully not-too-arrogant quotes:

"You should act in life in such a way that every person you meet wants to remember you and include you in the mere definition of its own existence"	This may be about true love, and true good. Note that making somebody part of your own definition goes far beyond acknowledging somebody, it gives her/him a bit of eternity, an existence beyond its body, it makes him/her a kind of divinity. Thus you should also be infinitely grateful to the persons whom you modified the existence in this way.
"Gaze at stars."	Because this is the philosophy of mens in south pacific. Because it makes you realize how tiny you are, and how lucky and unique you are, to have the opportunity to see how wonderful is the universe, to exist and have appeared precisely here and at this time. Because it gives you a destiny, a responsability as a human being, to act wisely in this tiny life and focus on what really matters. Because you can never feel lonely under the stars. Because it gives you hope that you can achieve a high-destiny, and strength in difficult situations.
"Et pourquoi pas ? (And why not?) "	This is what my great-father, René Jouannetaud, used to say. This is today one of my moto. He decided one day to start planting trees. And he planted no less than 30,000 trees in his life. He was not only extraordinary wise, but curious about everything, and deeply connected to the Earth, and Nature. He crafted my first dowser stick, and showed me how to use it. There is nothing like the deep connection you experience when you feel the stick turning in your hand on its own, and testing several times untill you realize you have found the underground river that passes through the village. I feel more than lucky to have known him. I naturally crafted his last stick when he returned to the earth.
"..."	Nothing. Because I do not consider I am so important as to give you advices. You are smart and strong enough to find your own way, to have your own philosophy your own belief and answers about the world, without needing anybody to tell you what to think, ever. It would be moreover offensive to the divinity inside you.

Odalric-Ambrym Maillard. The first picture was took in Carcassonne, the second one during the « Festival les 400 clous » in Lille, and the third one in Toulouse

« La première image illustre la quête de la vérité, la bataille, la fougue intellectuelle habitant le chercheur, pour aller vers son but, symbolisé par la troisième image. Celle-ci illustre l’apaisement intellectuel, le bonheur ressenti lors de la découverte d’un théorème, la contemplation du beau et du vrai, l’objet de la quête enfin. En ce sens le chercheur est un chevalier. La deuxième image relie ces deux mondes, par l’intermédiaire de ce clown ébobi ouvrant les bras. C’est ainsi que l’artiste expose tout son art. Ce clown est l’incarnation de la démarche scientifique, décalée, osant les idées les plus folles, et nécessitant l’émotion la plus productive pour accomplir sa tâche: le rire. Ce clown sans le sou traduit également l’humilité du chercheur, et le détachement des choses matérielles. Ainsi va le chercheur, chevalier, clown et artiste à la fois. »