Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Laurent Charlin"'
Publikováno v:
IEEE Open Journal of Intelligent Transportation Systems, Vol 5, Pp 238-250 (2024)
We introduce MuJAM, an adaptive traffic signal control method which leverages model-based reinforcement learning to 1) extend recent generalization efforts (to road network architectures and traffic distributions) further by allowing a generalization
Externí odkaz:
https://doaj.org/article/92d2952a76ca4d67b5b5d94108b55636
Publikováno v:
IEEE Open Journal of Intelligent Transportation Systems, Vol 5, Pp 2-15 (2024)
A number of deep reinforcement-learning (RL) approaches propose to control traffic signals. Compared to traditional approaches, RL approaches can learn from higher-dimensionality input road and vehicle sensors and better adapt to varying traffic cond
Externí odkaz:
https://doaj.org/article/9c2c683dbf4a4cc98f2824e41e3b8b20
Publikováno v:
Water, Vol 16, Iss 7, p 1042 (2024)
The jar test is the current standard method for predicting the performance of a conventional drinking water treatment (DWT) process and optimizing the coagulant dose. This test is time-consuming and requires human intervention, meaning it is infeasib
Externí odkaz:
https://doaj.org/article/efe3e8322ca04ed1bbe2cc4d81427672
Publikováno v:
IEEE Transactions on Intelligent Transportation Systems. 23:7496-7507
Scaling adaptive traffic-signal control involves dealing with combinatorial state and action spaces. Multi-agent reinforcement learning attempts to address this challenge by distributing control to specialized agents. However, specialization hinders
Publikováno v:
SSRN Electronic Journal.
Autor:
Ekaterina Kochmar, Laurent Charlin, Ansona Onyi Ching, Ariella Smofsky, Farid Faraji, Adela Matajova, Iulian Vlad Serban, Anush Stepanyan, Robert Belfer, Yoshua Bengio, Sabina Elkins, Muhammad Shayan, Vincent Pavero, Nathan Burns, Dung Do Vu, François St-Hilaire, Antoine Frau, Neroli Ko, Joseph Potochny
Publikováno v:
St-Hilaire, F, Burns, N, Belfer, R, Shayan, M, Smofsky, A, Vu, D D, Frau, A, Potochny, J, Faraji, F, Pavero, V, Ko, N, Ching, A O, Elkins, S, Stepanyan, A, Matajova, A, Charlin, L, Bengio, Y, Serban, I V & Kochmar, E 2021, ' A Comparative Study of Learning Outcomes for Online Learning Platforms ', Paper presented at The 2021 conference on Artificial Intelligence in Education, Utrecht, Netherlands, 14/06/21-18/06/21 .
Lecture Notes in Computer Science ISBN: 9783030782696
AIED (2)
Lecture Notes in Computer Science ISBN: 9783030782696
AIED (2)
Personalization and active learning help educational systems to close the gap between students with varying abilities. We run a comparative head-to-head study of learning outcomes for two popular online platforms: Platform A, which delivers content o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d221bedce6209909921af1851e63899c
https://purehost.bath.ac.uk/ws/files/219767691/paper_195.pdf
https://purehost.bath.ac.uk/ws/files/219767691/paper_195.pdf
Publikováno v:
MLSP
Latent-variable generative models offer a principled solution for modeling and sampling from complex probability distributions. Implementing a joint training objective with a complex prior, however, can be a tedious task, as one is typically required
Autor:
Iulian Vlad Serban, Aaron Courville, Dung Do Vu, Robert Belfer, Joelle Pineau, Ekaterina Kochmar, Laurent Charlin, Varun Gupta, Yoshua Bengio
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030522391
AIED (2)
Artificial Intelligence in Education
AIED (2)
Artificial Intelligence in Education
We present Korbit, a large-scale, open-domain, mixed-interface, dialogue-based intelligent tutoring system (ITS). Korbit uses machine learning, natural language processing and reinforcement learning to provide interactive, personalized learning onlin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::62024e826ae4b12a22850012753fc19e
Publikováno v:
EMNLP (1)
Multi-document summarization is a challenging task for which there exists little large-scale datasets. We propose Multi-XScience, a large-scale multi-document summarization dataset created from scientific articles. Multi-XScience introduces a challen