19 citations
- Rémy Portelas2 profiles4 · h 8
- Antoine Houdard3 · h 7
- Anthony Kobanda2 · h 2
- Grgur Kovač2 · h 7
- Ludovic Denoyer2 · h 31
- Masataka Sawayama2 profiles2 · h 11
- Odalric-Ambrym Maillard2 · h 27
- Pierre Le Pelletier de Woillemont2 · h 2
- P. Oudeyer2 · h 56
- Rémi Labory2 · h 2
- V. Corruble2 · h 16
- Alin Cristian Rosoiu1 · h 1
- Centre National de la Recherche ScientifiqueFR3 papers
- Sorbonne UniversitéFR3 papers
- Ubisoft (Canada)CA2 papers
- Université de BordeauxFR2 papers
- California Institute of TechnologyUS1 paper
- Canadian Institute for Advanced ResearchCA1 paper
- Centre Universitaire de MilaDZ1 paper
- École Nationale Supérieure d'Ingénieurs de CaenFR1 paper
- Forge (United Kingdom)GB1 paper
- GREYCFR1 paper
- InsermFR1 paper
- Institut de Mathématiques de BordeauxFR1 paper
14 papers
A Continual Offline Reinforcement Learning Benchmark for Navigation Tasks
Anthony Kobanda, Odalric-Ambrym Maillard, Rémy Portelas
Autonomous agents operating in domains such as robotics or video game simulations must adapt to changing tasks without forgetting about the previous ones. This process called Conti…
Hierarchical Subspaces of Policies for Continual Offline Reinforcement Learning
Anthony Kobanda, Rémy Portelas, Odalric-Ambrym Maillard +1
We consider a Continual Reinforcement Learning setup, where a learning agent must continuously adapt to new tasks while retaining previously acquired skill sets, with a focus on th…
Stick to your Role! Stability of Personal Values Expressed in Large Language Models
Grgur Kovač, Rémy Portelas, Masataka Sawayama +2
The standard way to study Large Language Models (LLMs) with benchmarks or psychology questionnaires is to provide many different queries from similar minimal contexts (e.g. multipl…
Real-Time Neural Materials using Block-Compressed Features
Clément Weinreich, Louis de Oliveira, Antoine Houdard +1
Neural materials typically consist of a collection of neural features along with a decoder network. The main challenge in integrating such models in real-time rendering pipelines l…
Towards Detecting Contextual Real-Time Toxicity for In-Game Chat
Zachary Yang, Nicolas Grenan-Godbout, Reihaneh Rabbany
Real-time toxicity detection in online environments poses a significant challenge, due to the increasing prevalence of social media and gaming platforms. We introduce ToxBuster, a…
Large Language Models as Superpositions of Cultural Perspectives
Grgur Kovač, Masataka Sawayama, Rémy Portelas +3
Large Language Models (LLMs) are often misleadingly recognized as having a personality or a set of values. We argue that an LLM can be seen as a superposition of perspectives with…