Portfolio item number 1
Short description of portfolio item number 1
Posts by Collection
portfolio
Portfolio item number 2
Short description of portfolio item number 2
projects
AnR AccelerAI
Published:
This is a description of the project!
publications
Learning intrinsically motivated options to stimulate policy exploration
Published in 4th Lifelong Machine Learning Workshop at ICML 2020, 2020
We study intrinsic motivation for exploration in RL and propose an aternative to the wide-spread approach of a weighted sum of rewards. We show that decoupling exploration and exploitation through different agents enables to scale to multiple intrinsic rewards, ignore harmful signals and improve task transfer. We propose to switch between agents through an Explore Option (an additional to call the Explorer agent), leading to exploration-focused Hierarchical RL.
Deep Learning of Intrinsically Motivated Options in the Arcade Learning Environment
Published in Deep Reinforcement Learning Workshop NeurIPS 2022, 2022
We extend Explore Options for Deep Reinforcement Learning, adapting the algorithms for neural-network-based function approximation through the off-policy training of multi-headed neural networks. We provide a clear framework on the different choices of combination of intrinsic and extrinsic rewards. We evaluate the methods on challenging Atari exploration games.
A Case for Representation-Based Successor Features for Transfer in Reinforcement Learning
Published in BNAIC/BeNeLearn 2022, 2022
Successor Features propose to linearly decompose the reward function through a basis of rewards or features, but leave the exact features undefined. We study different possible types of features and their impact on learning and task representation.
GPI-tree search: algorithms for decision-time planning with the general policy improvement theorem
Published in Adaptive Learning Agents Workshop of AAMAS 2023; Neural Computing and Applications, 2025
We study unsupervised skill discovery, and in particular the usage of learned skills during transfer. We propose to enhance the General Policy Improvement Theorem with a k-step forward search and show that it is possible to plan at the skill level with this approach and framework.
Successor Clusters: A Behavior Basis for Unsupervised Zero-Shot Reinforcement Learning
Published in Transactions on Machine Learning Research, 2025
We introduce a novel method for unsupervised zero-shot RL based on the partitioning of the state space into clusters of temporal proximity. We employ the Successor Feature framework, which allows us to train a general policy and visualize the expected optimal trajectories. We achieve state-of-the-art zero-shot performance for SF-based methods on MuJoCo tasks.
Transfer and Zero-shot Reinforcement Learning : Learning Behaviors without a Reward Function
Published in University of Antwerp, Faculty of Science, 2025
Manuscript of my PhD thesis. Study of unsupervised skill discovery and task transfer in reinforcement learning: learning behaviors and representations without reward to quickly maximize any downstream task reward.
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Techniques d’Apprentissage Automatique (TAA)
Cours de Master 2 Intelligence Artificielle, Université Lyon 1, Département d'Informatique, 2026
Cours d’introduction aux Techniques d’Apprentissage Automatique (Machine Learning, ML). Ce module a pour objectif de vous donner les bases pour exploiter des données et en extraire des connaissances. L’UE est divisée en trois: une partie apprentissage “classique” (Machine Learning), une partie apprentissage “profond” (Deep Learning) et une partie sur le déploiement de modèles (MLOps).