Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Bondoux, Nicolas"'
Autor:
Lhéritier, Alix, Bondoux, Nicolas
Distributional reinforcement learning (DRL) extends the value-based approach by approximating the full distribution over future returns instead of the mean only, providing a richer signal that leads to improved performances. Quantile Regression (QR)
Externí odkaz:
http://arxiv.org/abs/2110.00535
Autor:
Maschi, Fabio, Alonso, Gustavo, Hock-Koon, Anthony, Bondoux, Nicolas, Roy, Teddy, Boudia, Mourad, Casalino, Matteo
FPGAs are quickly becoming available in the cloud as a one more heterogeneous processing element complementing CPUs and GPUs. There are many reports in the literature showing the potential for FPGAs to accelerate a wide variety of algorithms, which c
Externí odkaz:
http://arxiv.org/abs/2108.09073
Autor:
Lhéritier, Alix, Bondoux, Nicolas
Distributional reinforcement learning (DRL) extends the value-based approach by using a deep convolutional network to approximate the full distribution over future returns instead of the mean only, providing a richer signal that leads to improved per
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::56210b73abccc29e582a779d709d65d1
https://hal.archives-ouvertes.fr/hal-03363669
https://hal.archives-ouvertes.fr/hal-03363669
Autor:
Lh��ritier, Alix, Bondoux, Nicolas
Distributional reinforcement learning (DRL) extends the value-based approach by approximating the full distribution over future returns instead of the mean only, providing a richer signal that leads to improved performances. Quantile Regression (QR)
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c2d891878191484c6ae4313389a61fa5
Publikováno v:
Journal of Revenue & Pricing Management; Dec2021, Vol. 20 Issue 6, p634-645, 12p
Autor:
Bondoux, Nicolas1 (AUTHOR), Nguyen, Anh Quan1 (AUTHOR), Fiig, Thomas2 (AUTHOR) thomas.fiig@amadeus.com, Acuna-Agost, Rodrigo1 (AUTHOR)
Publikováno v:
Journal of Revenue & Pricing Management. Oct2020, Vol. 19 Issue 5, p332-348. 17p.
Publikováno v:
Hjorth, R, Fiig, T, Bondoux, N & Larsen, J 2016, Joint overbooking and seat allocation for fare families .
Revenue Management Systems (RMS) traditionally solve the seat allocation problem separately from the overbooking problem. Overbooking is managed by inflating the authorization levels obtained from seat allocation by various heuristics. This approach
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______1202::7f9c771e78f748993e9eae8a7e97f8f5
https://orbit.dtu.dk/en/publications/joint-overbooking-and-seat-allocation-for-fare-families(eabb00a9-2e5f-47a9-a772-0abadb0f3ca0).html
https://orbit.dtu.dk/en/publications/joint-overbooking-and-seat-allocation-for-fare-families(eabb00a9-2e5f-47a9-a772-0abadb0f3ca0).html
Publikováno v:
Journal of Revenue & Pricing Management; Dec2018, Vol. 17 Issue 6, p436-452, 17p
Publikováno v:
Journal of Revenue & Pricing Management; Dec2017, Vol. 16 Issue 6, p621-639, 19p