7 papers
Retrieval-Augmented LLM Agents: Learning to Learn from Experience
Thomas Palmeira Ferraz, Romain Deffayet, Vassilina Nikoulina +2
While large language models (LLMs) have advanced the development of general-purpose agents, achieving robust generalization to unseen tasks remains a significant challenge. Current…
Robust Skills, Brittle Grounding: Diagnosing Restricted Generalization in Vision-Language Action Policies via Multi-Object Picking
David Emukpere, Romain Deffayet, Jean-Michel Renders
Vision-language action (VLA) policies often report strong manipulation benchmark performance with relatively few demonstrations, but it remains unclear whether this reflects robust…
RANa: Retrieval-Augmented Navigation
Gianluca Monaci, Rafael S. Rezende, Romain Deffayet +5
Methods for navigation based on large-scale learning typically treat each episode as a new problem, where the agent is spawned with a clean memory in an unknown environment. While…
Distributional Reinforcement Learning with Dual Expectile-Quantile Regression
Sami Jullien, Romain Deffayet, Jean-Michel Renders +2
Distributional reinforcement learning (RL) has proven useful in multiple benchmarks as it enables approximating the full distribution of returns and extracts rich feedback from env…
Disentangled Object-Centric Image Representation for Robotic Manipulation
David Emukpere, Romain Deffayet, Bingbing Wu +6
Learning robotic manipulation skills from vision is a promising approach for developing robotics applications that can generalize broadly to real-world scenarios. As such, many app…
An Offline Metric for the Debiasedness of Click Models
Romain Deffayet, Philipp Hager, Jean-Michel Renders +1
A well-known problem when learning from user clicks are inherent biases prevalent in the data, such as position or trust bias. Click models are a common method for extracting infor…