Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Romain Laroche"'
By the age of two, children tend to assume that new word categories are based on objects' shape, rather than their color or texture; this assumption is called the shape bias. They are thought to learn this bias by observing that their caregiver's lan
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f9dc6b7b958f5eb8b3c924e5de8405df
Publikováno v:
IJCAI
Malfunctioning neurons in the brain sometimes operate synchronously, reportedly causing many neurological diseases, e.g. Parkinson's. Suppression and control of this collective synchronous activity are therefore of great importance for neuroscience,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::91a4392ac6303d1c78e3cd9e1554615b
https://doi.org/10.24963/ijcai.2020/394
https://doi.org/10.24963/ijcai.2020/394
Publikováno v:
Computer Speech & Language. 47:93-111
This article introduces a new methodology to enhance an existing traditional Spoken Dialogue System (SDS) with optimal turn-taking capabilities in order to increase dialogue efficiency. A new approach for transforming the traditional dialogue archite
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4360bf5daf897e8d0ff7249f9741289c
https://doi.org/10.1016/j.csl.2017.07.006
https://doi.org/10.1016/j.csl.2017.07.006
Publikováno v:
Machine Learning and Knowledge Discovery in Databases ISBN: 9783030461324
ECML/PKDD (3)
ECML/PKDD (3)
Batch Reinforcement Learning (Batch RL) consists in training a policy using trajectories collected with another policy, called the behavioural policy. Safe policy improvement (SPI) provides guarantees with high probability that the trained policy per
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6f5e151d946d52443ff8d0a7588fcb1d
https://doi.org/10.1007/978-3-030-46133-1_4
https://doi.org/10.1007/978-3-030-46133-1_4
Publikováno v:
Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems
Delft University of Technology
Delft University of Technology
Previous work has shown the unreliability of existing algorithms in the batch Reinforcement Learning setting, and proposed the theoretically-grounded Safe Policy Improvement with Baseline Bootstrapping (SPIBB) fix: reproduce the baseline policy in th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8cadf9a5dbb81ced5846acaae381d603
http://arxiv.org/abs/1909.05236
http://arxiv.org/abs/1909.05236
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 32
In Reinforcement Learning, an intelligent agent has to make a sequence of decisions to accomplish a goal. If this sequence is long, then the agent has to plan over a long horizon. While learning the optimal policy and its value function is a well stu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f57c1d3de2ca540dafd76d9de287a610
https://doi.org/10.1609/aaai.v32i1.11646
https://doi.org/10.1609/aaai.v32i1.11646
Publikováno v:
SIGDIAL/SEMDIAL joint special session on negotiation dialog 2017
SIGDIAL/SEMDIAL joint special session on negotiation dialog 2017, Aug 2017, Saarbrücken, Germany
SIGDIAL/SEMDIAL joint special session on negotiation dialog 2017, Aug 2017, Saarbrücken, Germany
International audience; We address the problem of user adaptation in Spoken Dialogue Systems. The goal is to quickly adapt online to a new user given a large amount of dialogues collected with other users. Previous works using Transfer for Reinforcem
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::25a942f786600d3e57e3c767462c0e3b
https://doi.org/10.21437/semdial.2017-15
https://doi.org/10.21437/semdial.2017-15
Publikováno v:
Lecture Notes in Electrical Engineering ISBN: 9789811025846
IWSDS
IWSDS
User satisfaction is often considered as the objective that should be achieved by spoken dialogue systems. This is why the reward function of Spoken Dialogue Systems (SDS) trained by Reinforcement Learning (RL) is often designed to reflect user satis
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dfd8dbdb758efcfc3afb13ab62f2de9d
https://doi.org/10.1007/978-981-10-2585-3_3
https://doi.org/10.1007/978-981-10-2585-3_3
Publikováno v:
Lecture Notes in Electrical Engineering ISBN: 9789811025846
IWSDS
IWSDS
This chapter introduces a simulator for incremental human-machine dialogue in order to generate artificial dialogue datasets that can be used to train and test data-driven methods. We review the various simulator components in detail, including an un
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4208e6285f13d7be6f3426d6b7cfe15f
https://doi.org/10.1007/978-981-10-2585-3_4
https://doi.org/10.1007/978-981-10-2585-3_4
Autor:
Romain Laroche, Aude Genevay
Publikováno v:
Lecture Notes in Electrical Engineering ISBN: 9789811025846
IWSDS
IWSDS
This article presents the design of a generic negotiation dialogue game between two or more players. The goal is to reach an agreement, each player having his own preferences over a shared set of options. Several simulated users have been implemented
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ed1bcc7ee208db15fe3d165dcadd9b0d
https://doi.org/10.1007/978-981-10-2585-3_33
https://doi.org/10.1007/978-981-10-2585-3_33