40 citations · 134 across the 40 of their papers we have counts for
44 papers
Behavioral Foundation Models for Quality Diversity
Nazim Bendib, Nicolas Perrin-Gilbert, Olivier Sigaud
Behavioral Foundation Models (BFMs) are an emerging paradigm in reinforcement learning, playing a role analogous to large language models in natural language processing: they have…
A Sim-to-Real Integration Pipeline for Training and Deployment of Chunk-Based VLA Manipulation Policies
Mathilde Kappel, Clémence Grislain, Mohamed Chetouani +5
Vision-Language-Action (VLA) models have become a prominent paradigm for mapping multimodal inputs, including semantic instructions, visual observations of the scene, and proprioce…
Locally-Guided Actor-Critic: Training a Goal-conditioned Actor with a Subgoal-aware Critic
Olivier Serris, Stéphane Doncieux, Olivier Sigaud
Goal-conditioned reinforcement learning struggles with long horizons when rewards are sparse. While a planner can provide subgoals to guide a low-level policy, its use at test time…
PRISM: Perception Reasoning Interleaved for Sequential Decision Making
Mohamed Salim Aissi, Clemence Grislain, Clement Romac +4
Scaling LLM-based embodied agents from text-only environments to complex multimodal settings remains a major challenge. Recent work identifies a perception-reasoning-decision gap i…
MODIP: Efficient Model-Based Optimization for Diffusion Policies
Zakariae El Asri, Philippe Gratias-Quiquandon, Nicolas Thome +1
Diffusion policies (DPs) have emerged as expressive policy representations for robot learning, often used with imitation learning methods such as behavioral cloning (BC). However,…
IntentVLM: Open-Vocabulary Intention Recognition through Forward-Inverse Modeling with Video-Language Models
Hamed Rahimi, Clemence Grislain, Adrien Jacquet Cretides +2
Improving the effectiveness of human-robot interaction requires social robots to accurately infer human goals through robust intention understanding. This challenge is particularly…
Improving Zero-Shot Offline RL via Behavioral Task Sampling
Nazim Bendib, Nicolas Perrin-Gilbert, Olivier Sigaud
Offline zero-shot reinforcement learning (RL) aims to learn agents that optimize unseen reward functions without additional environment interaction. The standard approach to this p…
Online Self-Training for Co-Adaptation in Hierarchical Diffusion Policies
Clemence Grislain, Mathilde Kappel, Olivier Sigaud +1
Hierarchical policies decompose language-conditioned long-horizon robotic manipulation into a high-level planner and a low-level controller. However, effective coordination between…
Controlling Intent Expressiveness in Robot Motion with Diffusion Models
Wenli Shi, Clemence Grislain, Olivier Sigaud +1
Legibility of robot motion is critical in human-robot interaction, as it allows humans to quickly infer a robot's intended goal. Although traditional trajectory generation methods…
RT-HCP: Dealing with Inference Delays and Sample Efficiency to Learn Directly on Robotic Platforms
Zakariae El Asri, Ibrahim Laiche, Clément Rambour +2
Learning a controller directly on the robot requires extreme sample efficiency. Model-based reinforcement learning (RL) methods are the most sample efficient, but they often suffer…
I-FailSense: Towards General Robotic Failure Detection with Vision-Language Models
Clemence Grislain, Hamed Rahimi, Olivier Sigaud +1
Language-conditioned robotic manipulation in open-world settings requires not only accurate task execution but also the ability to detect failures for robust deployment in real-wor…
HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents
Thomas Carta, Clément Romac, Loris Gaven +3
We study goal-conditioned reinforcement learning in partially observable environments with sparse rewards and large, structured goal spaces. In such settings, complex goals often r…
Imagine Beyond! Distributionally Robust Auto-Encoding for State Space Coverage in Online Reinforcement Learning
Nicolas Castanet, Olivier Sigaud, Sylvain Lamprier
Goal-Conditioned Reinforcement Learning (GCRL) enables agents to autonomously acquire diverse behaviors, but faces major challenges in visual environments due to high-dimensional,…
A tale of two goals: leveraging sequentiality in multi-goal scenarios
Olivier Serris, Stéphane Doncieux, Olivier Sigaud
Several hierarchical reinforcement learning methods leverage planning to create a graph or sequences of intermediate goals, guiding a lower-level goal-conditioned (GC) policy to re…
VIPER: Visual Perception and Explainable Reasoning for Sequential Decision-Making
Mohamed Salim Aissi, Clemence Grislain, Mohamed Chetouani +3
While Large Language Models (LLMs) excel at reasoning on text and Vision-Language Models (VLMs) are highly effective for visual perception, applying those models for visual instruc…
MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces
Loris Gaven, Thomas Carta, Clément Romac +4
Open-ended learning agents must efficiently prioritize goals in vast possibility spaces, focusing on those that maximize learning progress (LP). When such autotelic exploration is…
Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting
Mohamed Salim Aissi, Clement Romac, Thomas Carta +5
Reinforcement learning (RL) is a promising approach for aligning large language models (LLMs) knowledge with sequential decision-making tasks. However, few studies have thoroughly…
SAC-GLAM: Improving Online RL for LLM agents with Soft Actor-Critic and Hindsight Relabeling
Loris Gaven, Clement Romac, Thomas Carta +3
The past years have seen Large Language Models (LLMs) strive not only as generative models but also as agents solving textual sequential decision-making tasks. When facing complex…
From Goal-Conditioned to Language-Conditioned Agents via Vision-Language Models
Theo Cachet, Christopher R. Dance, Olivier Sigaud
Vision-language models (VLMs) have tremendous potential for grounding language, and thus enabling language-conditioned agents (LCAs) to perform diverse tasks specified with text. T…
Physics-Informed Model and Hybrid Planning for Efficient Dyna-Style Reinforcement Learning
Zakariae El Asri, Olivier Sigaud, Nicolas Thome
Applying reinforcement learning (RL) to real-world applications requires addressing a trade-off between asymptotic performance, sample efficiency, and inference time. In this work,…
Single-Reset Divide & Conquer Imitation Learning
Alexandre Chenu, Olivier Serris, Olivier Sigaud +1
Demonstrations are commonly used to speed up the learning process of Deep Reinforcement Learning algorithms. To cope with the difficulty of accessing multiple demonstrations, some…
A Definition of Open-Ended Learning Problems for Goal-Conditioned Agents
Olivier Sigaud, Gianluca Baldassarre, Cedric Colas +5
A lot of recent machine learning research papers have ``open-ended learning'' in their title. But very few of them attempt to define what they mean when using the term. Even worse,…
An Open-Loop Baseline for Reinforcement Learning Locomotion Tasks
Antonin Raffin, Olivier Sigaud, Jens Kober +3
In search of a simple baseline for Deep Reinforcement Learning in locomotion tasks, we propose a model-free open-loop strategy. By leveraging prior knowledge and the elegance of si…
Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning
Thomas Carta, Clément Romac, Thomas Wolf +3
Recent works successfully leveraged Large Language Models' (LLM) abilities to capture abstract knowledge about world's physics to solve decision-making problems. Yet, the alignment…