Real-time retrieval for case-based reasoning in interactive multiagent-based simulations

Autor: De Loor, Pierre, Bénard, Romain, Pierre, Chevaillier

Publikováno v: Expert Systems with Applications 38, 5 (2011) 5145-5153

The aim of this paper is to present the principles and results about case-based reasoning adapted to real- time interactive simulations, more precisely concerning retrieval mechanisms. The article begins by introducing the constraints involved in int

Externí odkaz: http://arxiv.org/abs/1107.3326

Unsupervised Learning of State Representation using Balanced View Spatial Deep InfoMax: Evaluation on Atari Games

Autor: Menore Mengistu, Getachew Alemu, Pierre Chevaillier, Pierre De Loor

Publikováno v: Proceedings of the 14th International Conference on Agents and Artificial Intelligence.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::b716361fba55b18879a3662c7f64c0c7
https://doi.org/10.5220/0010785000003116

Hierarchical Temporal Memories Prediction Performance and Robustness to Faults on Multivariate Time Series

Autor: Mathieu Jégou, Pierre Chevaillier, Pierre De Loor

Publikováno v: ICMLA
18th International Conference on Machine Learning and Applications (ICMLA 2019), special session on Machine Learning for Predictive Models in Engineering Applications
18th International Conference on Machine Learning and Applications (ICMLA 2019), special session on Machine Learning for Predictive Models in Engineering Applications, Dec 2019, Boca Raton, FL, United States

International audience; In this article, we evaluate the ability of Hierarchical Temporal Memories (HTM) to process values coming from sensor chains. We present a study on the impact of the HTM parameterization on its ability to predict input values

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::06ef33bb7b7fb4bf6a5219be375551b3
https://doi.org/10.1109/icmla.2019.00294

A computational model for the emergence of turn-taking behaviors in user-agent interactions

Autor: Mathieu Jégou, Pierre Chevaillier

Publikováno v: Journal on Multimodal User Interfaces
Journal on Multimodal User Interfaces, Springer, 2018, 12 (3), pp.199-223. ⟨10.1007/s12193-018-0265-3⟩

We propose a computational model that endows conversational agents with the capability to coordinate their speaking turns (turn-taking management) in the context of mixed-initiative two-party dialogs. In human conversations, participants are continuo

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eec7d2d47243fe40204f8df720ca29d5
https://hal.archives-ouvertes.fr/hal-02495934

Collaborative virtual training with physical and communicative autonomous agents

Autor: Rozenn Bouville, Mukesh Barange, Pierre Chevaillier, Paul Evrard, Florian Nouviale, Thomas Lopez, Valérie Gouranton, Bruno Arnaldi

Publikováno v: Computer Animation and Virtual Worlds. 25:485-493

Virtual agents are a real asset in collaborative virtual environment for training CVET as they can replace missing team members. Collaboration between such agents and users, however, is generally limited. We present here a whole integrated model of C

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::acac631afbe52d278567600ec40eaa9b
https://doi.org/10.1002/cav.1583