471 citations
- Lyon 1 UniversitéFR95 papers
- Centre National de la Recherche ScientifiqueFR92 papers
- Institut National des Sciences Appliquées de LyonFR59 papers
- École Centrale de LyonFR19 papers
- Institut national de recherche en sciences et technologies du numériqueFR18 papers
- Université de LyonFR16 papers
- Université Grenoble AlpesFR12 papers
- École Normale Supérieure de LyonFR10 papers
- LabEx PERSYVAL-LabFR10 papers
- Laboratoire d'Informatique, de Modélisation et d'Optimisation des SystèmesFR10 papers
- Universidade Federal de PernambucoBR8 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR7 papers
205 papers
Instance Discrimination for Link Prediction
Valentin Cuzin-Rambaud, Mathieu Lefort, Rémy Cazabet
Recently, instance discrimination models have emerged as a major solution for self-supervised learning. Having already demonstrated its effectiveness in the image domain, instance…
A Survey of Multi-Agent Deep Reinforcement Learning with Graph Neural Network-Based Communication
Valentin Cuzin-Rambaud, Laetitia Matignon, Maxime Morge
In multi-agent reinforcement learning (MARL), the integration of a communication mechanism, allowing agents to better learn to coordinate their actions and converge on their object…
Large Language Models and Algorithm Execution: Application to an Arithmetic Function
Farah Ben Slama, Frédéric Armetta
Large Language Models (LLMs) have recently developed new advanced functionalities. Their effectiveness relies on statistical learning and generalization capabilities. However, they…
PAC-Bayesian Reinforcement Learning Trains Generalizable Policies
Abdelkrim Zitouni, Mehdi Hennequin, Juba Agoun +3
We derive a novel PAC-Bayesian generalization bound for reinforcement learning that explicitly accounts for Markov dependencies in the data, through the chain's mixing time. This c…
StimulHeat: a Low-Energy Wearable Thermal Feedback Device Using Peltier Elements with Heat Flow Controlled Loop for Hand Interactions in Virtual Reality
Matthieu Mesnage, Sophie Villenave, Bertrand Massot +4
Nowadays, the majority of wearable thermal feedback systems designed for use in virtual reality applications are not compatible or not integrated to standard controllers and are ba…
Robotic Manipulation via Imitation Learning: Taxonomy, Evolution, Benchmark, and Challenges
Zezeng Li, Alexandre Chapin, Enda Xiang +6
Robotic Manipulation (RM) is central to the advancement of autonomous robots, enabling them to interact with and manipulate objects in real-world environments. This survey focuses…