M
Mathieu Seurin
Researcher at Lille University of Science and Technology
Publications - 12
Citations - 134
Mathieu Seurin is an academic researcher from Lille University of Science and Technology. The author has contributed to research in topics: Reinforcement learning & Hindsight bias. The author has an hindex of 6, co-authored 12 publications receiving 104 citations. Previous affiliations of Mathieu Seurin include Université Paris-Saclay & French Institute for Research in Computer Science and Automation.
Papers
More filters
Posted Content
Unsupervised state representation learning with robotic priors: a robustness benchmark
TL;DR: The results show that the robotic prior approach is able to extract high level representation as the 3D position of an arm and organize it into a compact and coherent space of states in a challenging dataset.
Book ChapterDOI
Visual Reasoning with Multi-hop Feature Modulation
Florian Strub,Mathieu Seurin,Ethan Perez,Harm de Vries,Jérémie Mary,Philippe Preux,Aaron Courville,Olivier Pietquin +7 more
TL;DR: It is demonstrated that multi-hop FiLM generation significantly outperforms prior state-of-the-art on the GuessWhat?! visual dialogue task and matches state- of-the art on the ReferIt object retrieval task, and additional qualitative analysis is provided.
Posted Content
Self-Educated Language Agent With Hindsight Experience Replay For Instruction Following
TL;DR: This article propose an orthogonal approach called Textual Hindsight experience replay (THER) that extends the Hindsight Experience Replay approach to the language setting, where whenever the agent does not fulfill its instruction, it learns to output a new directive that matches the agent trajectory, and relabels the episode with a positive reward.
Proceedings ArticleDOI
HIGhER: Improving instruction following with Hindsight Generation for Experience Replay
TL;DR: The authors propose an orthogonal approach called Hindsight Generation for Experience Replay (HIGhER) that extends the Hindsight Experience Replay approach to the language-conditioned policy setting.
Proceedings ArticleDOI
Deep unsupervised state representation learning with robotic priors: a robustness analysis
TL;DR: The results show that the robotic prior approach is able to extract high level representation as the 3D position of an arm and organize it into a compact and coherent space of states in a challenging dataset.