Sledovat
Nicolas Carrara
Nicolas Carrara
Qube Research And Technology, ex University of Toronto, SequeL/Inria, Orange Labs
E-mailová adresa ověřena na: inria.fr - Domovská stránka
Název
Citace
Citace
Rok
Budgeted reinforcement learning in continuous state space
N Carrara, E Leurent, R Laroche, T Urvoy, OA Maillard, O Pietquin
NeurIPS, 2019
232019
Microscopic model-based rl approaches for traffic signal control generalize better than model-free rl approaches
P Jaggi, X Wang, N Carrara, S Sanner, B Abdulhai
2021 IEEE International Intelligent Transportation Systems Conference (ITSC …, 2021
72021
A Fitted-Q Algorithm for Budgeted MDPs
N Carrara, R Laroche, JL Bouraoui, T Urvoy, O Pietquin
European Workshop on Reinforcement Learning (EWRL 2018), 2018
72018
Online learning and transfer for user adaptation in dialogue systems
N Carrara, R Laroche, O Pietquin
SIGDIAL/SEMDIAL joint special session on negotiation dialog 2017, 2017
42017
Safe transfer learning for dialogue applications
N Carrara, R Laroche, JL Bouraoui, T Urvoy, O Pietquin
SLSP 2018-6th International Conference on Statistical Language and Speech …, 2018
32018
Reinforcement learning for Dialogue Systems optimization with user adaptation.
N Carrara
Ecole Doctoral Science pour l'Ingénieur Université Lille Nord-de-France, 2019
22019
Quantitative Global Market-Making
N Carrara, B Arif
https://ncarrara.fr/others/myrill-tech-report.pdf, 2022
2022
Apprentissage par Renforcement pour l'optimisation des systèmes de dialogue via l'adaptation à l'utilisateur.
N Carrara
2019
Systém momentálně nemůže danou operaci provést. Zkuste to znovu později.
Články 1–8