no code implementations • 15 Feb 2024 • Quentin Gallouédec, Edward Beeching, Clément Romac, Emmanuel Dellandréa
The search for a general model that can operate seamlessly across multiple domains remains a key goal in machine learning research.
1 code implementation • 10 Jan 2023 • Thomas Duboudin, Emmanuel Dellandréa, Corentin Abgrall, Gilles Hénaff, Liming Chen
Deep neural networks do not discriminate between spurious and causal patterns, and will only learn the most predictive ones while ignoring the others.
no code implementations • 17 Oct 2022 • Thomas Duboudin, Emmanuel Dellandréa, Corentin Abgrall, Gilles Hénaff, Liming Chen
Indeed, test-time adaptation methods usually have to rely on a limited representation because of the shortcut learning phenomenon: only a subset of the available predictive patterns is learned with standard training.
1 code implementation • 31 Aug 2022 • Quentin Gallouédec, Emmanuel Dellandréa
In this paper, we introduce Latent Go-Explore (LGE), a simple and general approach based on the Go-Explore paradigm for exploration in reinforcement learning (RL).
1 code implementation • 25 Jun 2021 • Quentin Gallouédec, Nicolas Cazin, Emmanuel Dellandréa, Liming Chen
This technical report presents panda-gym, a set Reinforcement Learning (RL) environments for the Franka Emika Panda robot integrated with OpenAI Gym.
no code implementations • 15 Jun 2021 • Thomas Duboudin, Emmanuel Dellandréa, Corentin Abgrall, Gilles Hénaff, Liming Chen
Traditional deep learning algorithms often fail to generalize when they are tested outside of the domain of the training data.
no code implementations • 3 Feb 2020 • Amaury Depierre, Emmanuel Dellandréa, Liming Chen
Therefore, in this paper, we extend a state-of-the-art neural network with a scorer that evaluates the graspability of a given position, and introduce a novel loss function which correlates regression of grasp parameters with graspability score.
no code implementations • 18 Jun 2019 • Matthieu Grard, Emmanuel Dellandréa, Liming Chen
We thus also introduce a synthetic dataset of dense homogeneous object layouts, namely Mikado, which extensibly contains more instances and inter-instance occlusions per image than these public datasets.
no code implementations • 26 Sep 2018 • Maxime Petit, Amaury Depierre, Xiaofang Wang, Emmanuel Dellandréa, Liming Chen
In simulation, we demonstrate the benefit of the transfer learning based on visual similarity, as opposed to an amnesic learning (i. e. learning from scratch all the time).
1 code implementation • 30 Mar 2018 • Amaury Depierre, Emmanuel Dellandréa, Liming Chen
Jacquard is built on a subset of ShapeNet, a large CAD models dataset, and contains both RGB-D images and annotations of successful grasping positions based on grasp attempts performed in a simulated environment.
no code implementations • 4 Jan 2018 • Matthieu Grard, Romain Brégier, Florian Sella, Emmanuel Dellandréa, Liming Chen
We thus propose a step towards a practical interactive application for generating an object-oriented robotic grasp, requiring as inputs only one depth map of the scene and one user click on the next object to extract.