Search - Archive ouverte HAL Access content directly

Filter your results

38 Results
Domains : info
Image document

Hadoop for Roboticists

Olivier Deiss , Cedric Pradalier
[Research Report] UMI 2958 GeorgiaTech-CNRS. 2016
Reports hal-01435882v1

Faut-il minimiser le résidu de Bellman ou maximiser la valeur moyenne ?

Matthieu Geist , Bilal Piot , Olivier Pietquin
Journées Francophones sur la Planification, la Décision et l'Apprentissage pour la conduite de systèmes (JFPDA 2017), Jul 2017, Caen, France
Conference papers hal-01576347v1
Image document

Autonomous Mobile Systems for Long-Term Operations in Spatio-Temporal Environments

Cedric Pradalier
Robotics [cs.RO]. INP DE TOULOUSE, 2015
Habilitation à diriger des recherches tel-01435879v1
Image document

Bayesian Credible Intervals for Online and Active Learning of Classification Trees

Timothé Collet , Olivier Pietquin
ADPRL 2015 - Symposium on Adaptive Dynamic Programming and Reinforcement Learning., Dec 2015, Cape Town, South Africa
Conference papers hal-01225850v1

Design of a Multi-Strategy Parallelization for an Entire Application of Document Categorization on Low-Cost Multiprocessor PCs

Stéphane Vialle , Guillaume Schaeffer , Michel Ianotto
Studia Informatica Universalis, 2004, 3 (1), pp.61-84
Journal articles hal-01301161v1
Image document

Softened approximate policy iteration for Markov games

Julien Pérolat , Bilal Piot , Matthieu Geist , Bruno Scherrer , Olivier Pietquin et al.
ICML 2016 - 33rd International Conference on Machine Learning, Jun 2016, New York City, United States
Conference papers hal-01393328v1
Image document

CS8903 Special Problem : Mesh Networks for robotic teleoperation -State of the Art and Implementation for Robotics

Sylvain Chatel , Cedric Pradalier
[Research Report] UMI 2958 GeorgiaTech-CNRS. 2016
Reports hal-01435881v1
Image document

An algorithmic Survey of Parametric Value Function Approximation

Matthieu Geist , Olivier Pietquin
IEEE Transactions on Neural Networks and Learning Systems, 2013, 24 (6), pp.845-867. ⟨10.1109/TNNLS.2013.2247418⟩
Journal articles hal-00869725v1
Image document

Approximate modified policy iteration and its application to the game of Tetris

Bruno Scherrer , Mohammad Ghavamzadeh , Victor Gabillon , Boris Lesner , Matthieu Geist et al.
Journal of Machine Learning Research, 2015, 16, pp.1629−1676
Journal articles hal-01091341v1
Image document

Hybrid Co-simulation of FMUs using DEV&DESS in MECSYCO

Benjamin Camus , Virginie Galtier , Mathieu Caujolle , Vincent Chevrier , Julien Vaubourg et al.
[Research Report] Université de Lorraine, CNRS, Inria, LORIA, UMR 7503; CentraleSupélec UMI GT-CNRS 2958 Université Paris-Saclay; EDF - R&D MIRE/R44. 2016
Reports hal-01256738v1

A Simple Guideline for Code Optimizations on Modern Architectures with OpenACC and CUDA

Ludomir Oteski , Guillaume Colin-De-Verdière , Sylvain Contassot-Vivier , Stephane Vialle , Juliet Ryan et al.
GPU Technology Conference 2017, NVIDIA, May 2017, San Jose, United States
Conference papers hal-01527684v1

Optimism in Active Learning

Timothé Collet , Olivier Pietquin
Computational Intelligence and Neuroscience, 2015, 2015, pp.1--17. ⟨10.1155/2015/973696⟩
Journal articles hal-01225798v1
Image document

YARBUS : Yet Another Rule Based belief Update System Jérémy Fix Hervé Frezza-Buet

Jérémy Fix , Hervé Frezza-Buet
[Research Report] CentraleSupelec. 2015
Reports hal-01180218v1
Image document

Scaling of Distributed Multi-Simulations on Multi-Core Clusters

Cherifa Dad , Stephane Vialle , Mathieu Caujolle , Jean-Philippe Tavella , Michel Ianotto et al.
25th IEEE International Conference on Enabling Technologies: Infrastructure for Collaborative Enterprises (WETICE-2016), Jun 2016, Paris, France
Conference papers hal-01332628v1
Image document

Recherche locale de politique dans un espace convexe

Bruno Scherrer , Matthieu Geist
Revue des Sciences et Technologies de l'Information - Série RIA : Revue d'Intelligence Artificielle, 2015, 29 (6), pp.685-704. ⟨10.3166/RIA.29.685-706⟩
Journal articles hal-01275247v1
Image document

Optimism in Active Learning with Gaussian Processes

Timothé Collet , Olivier Pietquin
22nd International Conference on Neural Information Processing (ICONIP2015), Nov 2015, Istanbul, Turkey
Conference papers hal-01225826v1
Image document

Toward an Accurate and Fast Hybrid Multi-Simulation with the FMI-CS Standard

Jean-Philippe Tavella , Mathieu Caujolle , Stéphane Vialle , Cherifa Dad , Charles Tan et al.
21 st International Conference on: Emerging Technologies and Factory Automation (ETFA-2016), Sep 2016, Berlin, Germany
Conference papers hal-01371499v1
Image document

Score-based Inverse Reinforcement Learning

Layla El Asri , Bilal Piot , Matthieu Geist , Romain Laroche , Olivier Pietquin et al.
International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2016), May 2016, Singapore, Singapore
Conference papers hal-01406886v1
Image document

Towards a Unified CPU–GPU code hybridization: A GPU Based Optimization Strategy Efficient on Other Modern Architectures

Ludomir Oteski , Guillaume Colin de Verdière , Sylvain Contassot-Vivier , Stephane Vialle , Juliet Ryan et al.
Parallel Computing is Everywhere,, 2018
Book sections hal-01742774v1
Image document

Scaling FMI-CS Based Multi-Simulation Beyond Thousand FMUs on Infiniband Cluster

Stéphane Vialle , Jean-Philippe Tavella , Cherifa Dad , Remi Corniglion , Mathieu Caujolle et al.
12th International Modelica Conference 2017, May 2017, Prague, Czech Republic
Conference papers hal-01527682v1

Towards an Efficient CPU-GPU Code Hybridization: a Simple Guideline for Code Optimizations on Modern Architecture with OpenACC and CUDA

Ludomir Oteski , Guillaume Colin de Verdiere , Sylvain Contassot-Vivier , Stephane Vialle , Juliette Ryan et al.
GPU Technology Conference (GTC), Oct 2017, Munich, Germany
Conference papers hal-01651967v1
Image document

Toward an Hybrid Co-simulation with the FMI-CS Standard

Jean-Philippe Tavella , Mathieu Caujolle , Charles Tan , Gilles Plessis , Mathieu Schumann et al.
2016
Other publications hal-01301183v1

Compact and Interpretable Dialogue State Representation with Genetic Sparse Distributed Memory

Layla El Asri , Romain Laroche , Olivier Pietquin
7th International Workshop on Spoken Dialogue Systems (IWSDS 2016), Jan 2016, Saariselka, Finland
Conference papers hal-01406873v1
Image document

In the quest of efficient hardware implementations of dynamic neural fields: an experimental study on the influence of the kernel shape

Benoît Chappet de Vangel , Jérémy Fix
Intemational Joint Conference on Neural Networks (IJCNN), Jul 2016, Vancouver, Canada. ⟨10.1109/IJCNN.2016.7727446⟩
Conference papers hal-01482258v1
Image document

Evaluation of Off-The-Shelf CNNs for the Representation of Natural Scenes with Large Seasonal Variations

Amandine Gout , Yann Lifchitz , Titouan Cottencin , Quentin Groshens , Jérémy Fix et al.
[Research Report] UMI 2958 GeorgiaTech-CNRS; CentraleSupélec UMI GT-CNRS 2958 Université Paris-Saclay. 2017
Reports hal-01448091v2
Image document

Laugh When You’re Winning

Maurizio Mancini , Laurent Ach , Emeline Bantegnie , Tobias Baur , Nadia Berthouze et al.
9th International Summer Workshop on Multimodal Interfaces (eNTERFACE), Jul 2013, Lisbon, Portugal. pp.50-79, ⟨10.1007/978-3-642-55143-7_3⟩
Conference papers hal-01350739v1
Image document

A multiplicative UCB strategy for Gamma rewards

Matthieu Geist
European Workshop on Reinforcement Learning, 2015, Lille, France
Conference papers hal-01258820v1
Image document

Imitation Learning Applied to Embodied Conversational Agents

Bilal Piot , Matthieu Geist , Olivier Pietquin
4th Workshop on Machine Learning for Interactive Systems (MLIS 2015), Jul 2015, Lille, France
Conference papers hal-01225816v1

MECSYCO-DACCOSIM Coupling

Benjamin Camus , Mathieu Caujolle , Virginie Galtier
2015
Preprints, Working Papers, ... hal-01296707v1
Image document

Parallelization, Distribution and Scaling of Multi-Simulations on Multi-Core Clusters, with DACCOSIM Environment

Cherifa Dad , Stéphane Vialle , Mathieu Caujolle , Jean-Philippe Tavella , Michel Ianotto et al.
2016
Other publications hal-01289194v3