130 citations
- Laboratoire d'Informatique en Images et Systèmes d'InformationFR4 papers
- Lyon 1 UniversitéFR3 papers
- Institut National des Sciences Appliquées de LyonFR2 papers
- AgroécologieFR1 paper
- AGroécologie, Innovations, teRritoiresFR1 paper
- AgroParisTechFR1 paper
- Agropolis InternationalFR1 paper
- Amélioration Génétique et Adaptation des Plantes méditerranéennes et tropicalesFR1 paper
- Astrophysique, Instrumentation et ModélisationFR1 paper
- CEA CadaracheFR1 paper
- CEA GrenobleFR1 paper
- CEA Paris-SaclayFR1 paper
7 papers
VIRAL: Vision-grounded Integration for Reward design And Learning
Valentin Cuzin-Rambaud, Emilien Komlenovic, Alexandre Faure +1
The alignment between humans and machines is a critical challenge in artificial intelligence today. Reinforcement learning, which aims to maximize a reward function, is particularl…
MIRI-LRS spectrum of a cold exoplanet around a white dwarf: water, ammonia, and methane measurements
Maël Voyer, Quentin Changeat, Pierre-Olivier Lagage +21
The study of the atmosphere of exoplanets orbiting white dwarfs is a largely unexplored field. With WD\,0806-661\,b, we present the first deep dive into the atmospheric physics and…
Task-conditioned adaptation of visual features in multi-task policy learning
Pierre Marza, Laetitia Matignon, Olivier Simonin +1
Successfully addressing a wide variety of tasks is a core ability of autonomous agents, requiring flexibly adapting the underlying decision-making strategies and, as we argue in th…
Sequential annotations for naturally-occurring HRI: first insights
Lucien Tisserand, Frédéric Armetta, Heike Baldauf-Quilliatre +3
We explain the methodology we developed for improving the interactions accomplished by an embedded conversational agent, drawing from Conversation Analytic sequential and multimoda…
Adaptive reinforcement learning of multi-agent ethically-aligned behaviours: the QSOM and QDSOM algorithms
Rémy Chaput, Olivier Boissier, Mathieu Guillermin
The numerous deployed Artificial Intelligence systems need to be aligned with our ethical considerations. However, such ethical considerations might change as time passes: our soci…
AutoNeRF: Training Implicit Scene Representations with Autonomous Agents
Pierre Marza, Laetitia Matignon, Olivier Simonin +3
Implicit representations such as Neural Radiance Fields (NeRF) have been shown to be very effective at novel view synthesis. However, these models typically require manual and care…