In the context of the Inria project « Sequential Recommendation for Sustainable Gardening », we are opening a postdoc position, under super-vision by OA Maillard. This is a one year position, but it can easily be extended later on. The topic is on Real-Life Reinforcement Learning Challenges, as we are investigating novel challenges in Reinforcement Learning theory inspired by application of sequential decision making to fields like agroecology. On the theory side, this includes things such as Causal-RL, Contextual-RL and Robust-RL. The postdoc can work more on the theory side or more on the applied side acording ot his/her own taste. We are expected to investigate an exciting line of research with formalization and modeling of questions that deviate from RL mainstream formalization.
Please contact O-A. Maillard with 3 of your main publications, CV, motivation letter and recommendation letter.
In case you want to apply for PhD, I strongly encourage you to read (a substantial part of) the following books and lecture notes:
- Prediction Learning ang Games
Nicolo Cesa-Bianchi, and Gábor Lugosi. Cambridge University Press, 2006.
- Concentration inequalities: A nonasymptotic theory of independence
Stéphane Boucheron, Gábor Lugosi, and Pascal Massart. OUP Oxford, 2013.
- Self-normalized processes: Limit theory and Statistical Applications
Victor H. Peña, Tze Leung Lai, and Qi-Man Shao. Springer Science & Business Media, 2008.
- Pac-Bayesian supervised classification: The thermodynamics of statistical learning
Catoni, Olivier. IMS, 2007.
- Bandits algorithms
Tor Lattimore, Csaba Szepesvári.
- Algorithms for Reinforcement Learning
Csaba Szepesvári. Synthesis Lectures on Artificial Intelligence and Machine Learning 4.1 (2010): 1-103.
- Markov Decision Processes: Discrete Stochastic Dynamic Programming
- Mathematics of Statistical Sequentiel Decision Making.
Odalric-ambrym Maillard (my Habilitation dissertation).
- Statistical Learning Theory and Sequential Prediction
Alexander Rakhlin, Karthik Sridharan
- Concentration of Measure Inequalities in Information Theory, Communications and Coding,
Raginsky, Maxim, and Igal Sason. Now Publishers Inc., 2014.
- Course on Reinforcement Learning
Interns (summer 2021)
We have a list of (funded) internships proposals, please contact me in case you are interested. We expect students with a solid mathematical background specifically in statistics, information theory and/or dynamical systems.
- Challenges of Sequential Decision Modelling in AgroEcology: Real-life challenges beyond MDPs. Link.
- Revisiting Regression Trees and Random Forest with Bandits.
These are intended for Master 2 or outstanding Master 1 students, and generally open the possibility to start a PhD later on. If you are interested, go ahead and contact me directly.