David Bertoin defended his thesis on “Representations for generalization in reinforcement learning”

On Febuary 13, 2023, David Bertoin defended his thesis at ISAE-SUPAERO in Toulouse. While working on his thesis, David has been part of the DEEL project at IRT Saint Exupéry.


Representations for generalization in reinforcement learning


This thesis tackles the problem of learning image-based control policies in simulated environments. Despite their ability to learn such policies from interactions alone, deep reinforcement learning agents tend to memorize trajectories rather than discover state representations leading to the capability to generalize to new situations. This generalization problem hinders the adoption of reinforcement learning in the real world. Within this thesis, we study several aspects of the generalization problem through the prism of the representations an agent can learn of its environment.

First, we propose a method to increase the diversity of representations in a neural policy’s latent space, and promote agents’ robustness to spurious correlations between visual elements and rewards. Second, we consider generalization as robustness to distracting visual elements unobserved during training such as changing backgrounds. We present a method based on neural network interpretability to discover representations encoding crucial information while demonstrating invariance to visual distractions. Third, we consider generalization to situations containing similar semantic information but represented differently in distinct domains. We introduce a method to learn disentangled representations, disambiguating between the useful semantic information common between domains, and its complementary context information. These contributions constitute a step towards learning representations which help close the generalization gap in reinforcement learning.

Scientific publications


The DEEL (DEpendable Explainable Learning) project involves academic and industrial partners in the development of dependable, robust, explainable and certifiable artificial intelligence technological bricks applied to critical systems.

Emmanuel RACHELSONThesis directorISAE-SUPAERO
Sébastien GERCHINOVITZThesis co-directorUniversité Paul Sabatier
Olivier PIETQUINReviewerUniversité de Lille
Liam PAULLReviewerUniversité de Montréal
Vincent FRANÇOIS-LAVETExaminerVrije Universiteit Amsterdam
Matthieu GEISTExaminerUniversité de Lorraine
Amy ZHANGExaminerUniversity of Texas at Austin
David Bertoin defended his thesis on “Representations for generalization in reinforcement learning”
Scroll to top