Hugo Caselles-Dupré
Hugo Caselles-Dupré
PhD Candidate, Flowers Laboratory (ENSTA ParisTech and INRIA) & AI Lab (Softbank Robotics Europe)
Adresse e-mail validée de ensta.fr - Page d'accueil
TitreCitée parAnnée
Word2Vec applied to Recommendation: Hyperparameters Matter
H Caselles-Dupré, F Lesaint, J Royo-Letelier
RecSys '18 Proceedings of the 12th ACM Conference on Recommender Systems …, 2018
112018
Generative Models from the perspective of Continual Learning
T Lesort, H Caselles-Dupré, M Garcia-Ortiz, A Stoian, D Filliat
Published at ICJNN 2019 (Oral), 2018
52018
Flatland: a Lightweight First-Person 2-D Environment for Reinforcement Learning
H Caselles-Dupré, L Annabi, O Hagen, M Garcia-Ortiz, D Filliat
Workshop on Continual Unsupervised Sensorimotor Learning, ICDL-EpiRob 2018 …, 2018
42018
S-TRIGGER: Continual State Representation Learning via Self-Triggered Generative Replay
H Caselles-Dupré, M Garcia-Ortiz, D Filliat
arXiv preprint arXiv:1902.09434, 2019
32019
Continual State Representation Learning for Reinforcement Learning using Generative Replay
H Caselles-Dupré, M Garcia-Ortiz, D Filliat
Workshop on Continual Learning, NeurIPS 2018 (Neural Information Processing …, 2018
12018
DisCoRL: Continual Reinforcement Learning via Policy Distillation
R Traoré, H Caselles-Dupré, T Lesort, T Sun, G Cai, N Díaz-Rodríguez, ...
arXiv preprint arXiv:1907.05855, 2019
2019
Continual Reinforcement Learning deployed in Real-life using Policy Distillation and Sim2Real Transfer
R Traoré, H Caselles-Dupré, T Lesort, T Sun, N Diaz-Rodriguez, D Filliat
Workshop on Multi-Task and Lifelong Reinforcement Learning at ICML 2019, 2019
2019
Symmetry-Based Disentangled Representation Learning requires Interaction with Environments
H Caselles-Dupré, M Garcia-Ortiz, D Filliat
Task Agnostic Reinforcement Learning workshop (Oral), ICLR 2019., 2019
2019
Generative Models from the perspective of Continual Learning
M Garcia Ortiz, T Lesort, H Caselles-Dupré, JF Goudou, D Filliat
2018
Le système ne peut pas réaliser cette opération maintenant. Veuillez réessayer plus tard.
Articles 1–9