Segueix
Marc Abeille
Marc Abeille
Criteo
Correu electrònic verificat a ens-cachan.fr
Títol
Citada per
Citada per
Any
Linear thompson sampling revisited
M Abeille, A Lazaric
Artificial Intelligence and Statistics, 176-184, 2017
2532017
Improved regret bounds for thompson sampling in linear quadratic control problems
M Abeille, A Lazaric
International Conference on Machine Learning, 1-9, 2018
1042018
Improved optimistic algorithms for logistic bandits
L Faury, M Abeille, C Calauzènes, O Fercoq
International Conference on Machine Learning, 3052-3060, 2020
692020
Thompson sampling for linear-quadratic control problems
M Abeille, A Lazaric
Artificial intelligence and statistics, 1246-1254, 2017
662017
Efficient optimistic exploration in linear-quadratic regulators via lagrangian relaxation
M Abeille, A Lazaric
International Conference on Machine Learning, 23-31, 2020
392020
Instance-wise minimax-optimal algorithms for logistic bandits
M Abeille, L Faury, C Calauzènes
International Conference on Artificial Intelligence and Statistics, 3691-3699, 2021
262021
Thompson sampling in non-episodic restless bandits
YH Jung, M Abeille, A Tewari
arXiv preprint arXiv:1910.05654, 2019
242019
LQG for portfolio optimization
M Abeille, A Lazaric, X Brokmann
arXiv preprint arXiv:1611.00997, 2016
152016
Regret bounds for generalized linear bandits under parameter drift
L Faury, Y Russac, M Abeille, C Calauzenes
arXiv preprint arXiv:2103.05750, 2021
112021
Explicit shading strategies for repeated truthful auctions
M Abeille, C Calauzènes, NE Karoui, T Nedelec, V Perchet
arXiv preprint arXiv:1805.00256, 2018
92018
Jointly efficient and optimal algorithms for logistic bandits
L Faury, M Abeille, KS Jun, C Calauzènes
International Conference on Artificial Intelligence and Statistics, 546-580, 2022
82022
Real-time optimisation for online learning in auctions
L Croissant, M Abeille, C Calauzènes
International Conference on Machine Learning, 2217-2226, 2020
62020
Thresholding the virtual value: a simple method to increase welfare and lower reserve prices in online auction systems
T Nedelec, M Abeille, C Calauzènes, N El Karoui, B Heymann, V Perchet
arXiv preprint arXiv:1808.06979, 2018
62018
Diffusive limit approximation of pure-jump optimal stochastic control problems
M Abeille, B Bouchard, L Croissant
Journal of Optimization Theory and Applications 196 (1), 147-176, 2023
42023
A technical note on non-stationary parametric bandits: Existing mistakes and preliminary solutions
L Faury, Y Russac, M Abeille, C Calauzènes
Algorithmic Learning Theory, 619-626, 2021
32021
Thresholding at the monopoly price: an agnostic way to improve bidding strategies in revenue-maximizing auctions
T Nedelec, M Abeille, C Calauzènes, B Heymann, V Perchet, NE Karoui
arXiv preprint arXiv:1808.06979, 2018
12018
Near-continuous time Reinforcement Learning for continuous state-action spaces
L Croissant, M Abeille, B Bouchard
arXiv preprint arXiv:2309.02815, 2023
2023
Reinforcement Learning in near-continuous time for continuous state-action spaces
L Croissant, M Abeille, B Bouchard
Sixteenth European Workshop on Reinforcement Learning, 2023
2023
Diffusive limit approximation of pure jump optimal ergodic control problems
M Abeille, B Bouchard, L Croissant
2022
Optimal Regret Bounds for Generalized Linear Bandits under Parameter Drift
L Faury, Y Russac, M Abeille, C Calauzènes
Proceedings of Machine Learning Research vol 132, 1-37, 2021
2021
En aquests moments el sistema no pot dur a terme l'operació. Torneu-ho a provar més tard.
Articles 1–20