Accéder directement au contenu

Olivier Sigaud

154
Documents

Présentation

<http://people.isir.upmc.fr/sigaud> <http://people.isir.upmc.fr/sigaud/en>

Publications

Image document

Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: A Short Survey

Cédric Colas , Tristan Karch , Olivier Sigaud , Pierre-Yves Oudeyer
Journal of Artificial Intelligence Research, 2022, 74, ⟨10.1613/jair.1.13554⟩
Article dans une revue hal-03901771v1
Image document

An extensive appraisal of weight-sharing on the NAS-Bench-101 benchmark

Aloïs Pourchot , Kévin Bailly , Alexis Ducarouge , Olivier Sigaud
Neurocomputing, 2022, 498, pp.28-42. ⟨10.1016/j.neucom.2022.04.108⟩
Article dans une revue hal-03706214v1

CLIC: Curriculum Learning and Imitation for object Control in non-rewarding environments

Pierre Fournier , Cédric Colas , Mohamed Chetouani , Olivier Sigaud
IEEE Transactions on Cognitive and Developmental Systems, 2021, 13 (2), pp.239-248. ⟨10.1109/TCDS.2019.2933371⟩
Article dans une revue hal-02370859v1
Image document

Task Feasibility Maximization using Model-Free Policy Search and Model-Based Whole-Body Control

Ryan Lober , Olivier Sigaud , Vincent Padois
Frontiers in Robotics and AI, 2020, 7, ⟨10.3389/frobt.2020.00061⟩
Article dans une revue hal-01620370v3
Image document

Interactively shaping robot behaviour with unlabeled human instructions

Anis Najar , Olivier Sigaud , Mohamed Chetouani
Autonomous Agents and Multi-Agent Systems, 2020, 34 (2), ⟨10.1007/s10458-020-09459-6⟩
Article dans une revue hal-02996137v1
Image document

Mice adaptively generate choice variability in a deterministic task

Marwen Belkaid , Elise Bousseyrol , Romain Durand-de Cuttoli , Malou Dongelmans , Etienne K Duranté
Communications Biology, 2020, 3, pp.34. ⟨10.1038/s42003-020-0759-x⟩
Article dans une revue hal-02485779v1
Image document

Policy search in continuous action domains: An overview

Olivier Sigaud , Freek Stulp
Neural Networks, 2019, 113, pp.28-40. ⟨10.1016/j.neunet.2019.01.011⟩
Article dans une revue hal-02182466v1
Image document

Open-Ended Learning: A Conceptual Framework Based on Representational Redescription

Stéphane Doncieux , David Filliat , Natalia Díaz-Rodríguez , Timothy Hospedales , Richard Duro
Frontiers in Neurorobotics, 2018, 12, pp.59. ⟨10.3389/fnbot.2018.00059⟩
Article dans une revue hal-01889947v1

Identification of invariant sensorimotor structures as a prerequisite for the discovery of objects

Nicolas Lehir , Alban Laflaquière , Olivier Sigaud
Frontiers in Robotics and AI, 2018, 5, pp.70. ⟨10.3389/frobt.2018.00070⟩
Article dans une revue hal-03124279v1
Image document

Unifying Speed-Accuracy Trade-Off and Cost-Benefit Trade-Off in Human Reaching Movements

Luka Peternel , Olivier Sigaud , Jan Babič
Frontiers in Human Neuroscience, 2017, 11, pp.615. ⟨10.3389/fnhum.2017.00615⟩
Article dans une revue hal-01679624v1
Image document

The CoDyCo Project achievements and beyond: Towards Human Aware Whole-body Controllers for Physical Human Robot Interaction

Francesco Romano , Gabriele Nava , Morteza Azad , Jernej Camernik , Stefano Dafarra
IEEE Robotics and Automation Letters, 2017, ⟨10.1109/LRA.2017.2768126⟩
Article dans une revue hal-01620789v1
Image document

Towards Deep Developmental Learning

Olivier Sigaud , Alain Droniou
IEEE Transactions on Cognitive and Developmental Systems, 2016, 8 (2), pp.99-114. ⟨10.1109/TAMD.2015.2496248⟩
Article dans une revue hal-01331799v1
Image document

Experimental predictions drawn from a computational model of sign-trackers and goal-trackers

Florian Lesaint , Olivier Sigaud , Jeremy J. Clark , Shelly B. Flagel , Mehdi Khamassi
Journal of Physiology - Paris, 2015, 109 (1-3), pp.78-86. ⟨10.1016/j.jphysparis.2014.06.001⟩
Article dans une revue hal-01219979v1
Image document

Many regression algorithms, one unified model — A review

Freek Stulp , Olivier Sigaud
Neural Networks, 2015, 69, pp.60-79. ⟨10.1016/j.neunet.2015.05.005⟩
Article dans une revue hal-01162281v2
Image document

Deep unsupervised network for multimodal perception, representation and classification

Alain Droniou , Serena Ivaldi , Olivier Sigaud
Robotics and Autonomous Systems, 2015, 71, pp.83-98. ⟨10.1016/j.robot.2014.11.005⟩
Article dans une revue hal-01083521v1
Image document

Accounting for Negative Automaintenance in Pigeons: A Dual Learning Systems Approach and Factored Representations

Florian Lesaint , Olivier Sigaud , Mehdi Khamassi
Article dans une revue hal-01219998v1
Image document

Modelling Individual Differences in the Form of Pavlovian Conditioned Approach Responses: A Dual Learning Systems Approach with Factored Representation

Florian Lesaint , Olivier Sigaud , Shelly B. Flagel , Terry E. Robinson , Mehdi Khamassi
PLoS Computational Biology, 2014, 10 (2), pp.e1003466. ⟨10.1371/journal.pcbi.1003466⟩
Article dans une revue hal-00947727v1

Robot initiative in a team learning task increases the rhythm of interaction but not the perceived engagement

Serena Ivaldi , Salvatore Anzalone , Woody Rousseau , Olivier Sigaud , Mohamed Chetouani
Frontiers in Neurorobotics, 2014, 8, ⟨10.3389/fnbot.2014.00005⟩
Article dans une revue hal-02423102v1

Adaptation de la matrice de covariance pour l'apprentissage par renforcement direct

Olivier Sigaud , Freek Stulp
Revue des Sciences et Technologies de l'Information - Série RIA : Revue d'Intelligence Artificielle, 2013, 27 (2), pp.243-263. ⟨10.3166/ria.27.243-263⟩
Article dans une revue hal-00922127v1
Image document

The anticipatory construction of reality as a central concern for psychology and robotics

Olivier Sigaud , Martin Butz , Giovanni Pezzulo , Oliver Herbort
New Ideas in Psychology, 2013, 31, pp.217-220. ⟨10.1016/j.newideapsych.2012.12.004⟩
Article dans une revue hal-03124280v1
Image document

Object learning through active exploration

Serena Ivaldi , Sao Mai Nguyen , Natalia Lyubova , Alain Droniou , Vincent Padois
IEEE Transactions on Autonomous Mental Development, 2013, pp.1-18. ⟨10.1109/TAMD.2013.2280614⟩
Article dans une revue hal-00919694v1

Robot Skill Learning: From Reinforcement Learning to Evolution Strategies

Freek Stulp , Olivier Sigaud
Paladyn: Journal of Behavioral Robotics, 2013, 4 (1), pp.49-61
Article dans une revue hal-00922132v1
Image document

From humans to humanoids: the optimal control framework

Serena Ivaldi , Olivier Sigaud , Bastien Berret , Franscesco Nori
Paladyn: Journal of Behavioral Robotics, 2012, 3 (2), pp.75-91
Article dans une revue hal-03124283v1

Xcsf with local deletion: preventing detrimental forgetting

Martin Butz , Olivier Sigaud
Evolutionary Intelligence, 2012, 5, pp.117-127
Article dans une revue hal-03124282v1

Function approximation with lwpr and xcsf: a comparative study

Patrick Stalph , Jeremy Rubinsztajn , Olivier Sigaud , Martin Butz
Evolutionary Intelligence, 2012, 5, pp.103-116
Article dans une revue hal-03124281v1

A machine learning approach to reaching tasks

Didier Marin , Olivier Sigaud
Computer Methods in Biomechanics and Biomedical Engineering, 2012, 15 (sup1), pp.151-152. ⟨10.1080/10255842.2012.713684⟩
Article dans une revue hal-00743364v1
Image document

On-line regression algorithms for learning mechanical models of robots: a survey

Olivier Sigaud , Camille Salaün , Vincent Padois
Robotics and Autonomous Systems, 2011, 59 (12), pp.1115-1129. ⟨10.1016/j.robot.2011.07.006⟩
Article dans une revue hal-00629133v1

Apprentissage par renforcement factorisé pour le comportement de personnages non joueurs

Thomas Degris , Olivier Sigaud , Pierre-Henri Wuillemin
Revue des Sciences et Technologies de l'Information - Série RIA : Revue d'Intelligence Artificielle, 2009, 23 (2-3), pp.221-251
Article dans une revue hal-01170353v1
Image document

A comparison between atnosferes and lcss on non-markov problems

Samuel Landau , Olivier Sigaud
Information Sciences, 2008, 178, pp.4482-4500
Article dans une revue hal-03124284v1
Image document

Learning classifier systems: a survey

Olivier Sigaud , Stewart Wilson
Soft Computing, 2007, 11 (11), pp.1065-1078. ⟨10.1007/s00500-007-0164-0⟩
Article dans une revue hal-03124285v1

Les systèmes de classeurs : un état de l'art

Olivier Sigaud
Revue des Sciences et Technologies de l'Information - Série RIA : Revue d'Intelligence Artificielle, 2007, 21 (1), pp.75-106. ⟨10.3166/ria.21.75-106⟩
Article dans une revue hal-01185706v1

GACS : une approche ascendante pour la coordination spatiale

Fabien Flacher , Olivier Sigaud
Revue des Sciences et Technologies de l'Information - Série RIA : Revue d'Intelligence Artificielle, 2006, 20 (1), pp.7-30
Article dans une revue hal-01185691v1
Image document

Combining latent learning with dynamic programming in the modular anticipatory classifier system

Pierre Gérard , Jean-Arcady Meyer , Olivier Sigaud
European Journal of Operational Research, 2005, 160 (3), pp.614-637. ⟨10.1016/j.ejor.2003.10.004⟩
Article dans une revue hal-03124277v1

Rapid response of head direction cells to reorienting visual cues: A computational model

Thomas Degris , Olivier Sigaud , Sidney I Wiener , Angelo Arleo
Neurocomputing, 2004, 58-60, pp.675-682. ⟨10.1016/j.neucom.2004.01.113⟩
Article dans une revue hal-01185700v1

Apprentissage par renforcement indirect dans les systèmes de classeurs

Pierre Gérard , Olivier Sigaud
JEDAI - Journal électronique d'intelligence artificielle, 2004, 4, pp.19
Article dans une revue hal-01185705v1

Coordination spatiale émergente par champs de potentiel

Fabien Flacher , Olivier Sigaud
Revue des Sciences et Technologies de l'Information - Série TSI : Technique et Science Informatiques, 2003, 22 (2), pp.171-195. ⟨10.3166/tsi.22.171-195⟩
Article dans une revue hal-01184953v1

YACS : Yet a new Learning Classifier System using Anticipation.

Pierre Gérard , Wolfgang Stolzmann , Olivier Sigaud
Soft Computing, 2002, 6 (3-4), pp.216-228. ⟨10.1007/s005000100117⟩
Article dans une revue hal-01184970v1

Généralisation et apprentissage latent dans les systèmes de classeurs

Pierre Gérard , Olivier Sigaud
Extraction de connaissances et apprentissage, 2001, 1 (3), pp.87-114
Article dans une revue hal-01184979v1
Image document

Co-Apprentissage Humain-Machine: Cas d'Étude en Acquisition de Compétences Motrices

Vaynee Sungeelee , Antoine Loriette , Olivier Sigaud , Baptiste Caramiaux
34ème conférence Francophone sur l'Interaction Humain-Machine, Apr 2023, Troyes, France
Communication dans un congrès hal-03992717v1
Image document

Neural Architecture Search for Fracture Classification

Aloïs Pourchot , Kevin Bailly , Alexis Ducarouge , Olivier Sigaud
29th IEEE International Conference on Image Processing (ICIP 2022), Oct 2022, Bordeaux, France
Communication dans un congrès hal-03753702v1
Image document

EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RL

Thomas Carta , Sylvain Lamprier , Pierre-Yves Oudeyer , Olivier Sigaud
NeurIPS 2022 - Thirty-sixth Conference on Neural Information Processing Systems, Nov 2022, Nouvelle-Orléans, United States
Communication dans un congrès hal-03902423v1
Image document

DIVERSITY POLICY GRADIENT FOR SAMPLE EFFI-CIENT QUALITY-DIVERSITY OPTIMIZATION

Thomas Pierrot , Valentin Macé , Felix Chalumeau , Arthur Flajolet , Geoffrey Cideron
Workshop on Agent Learning in Open-Endedness (ALOE) at ICLR 2022, 2022, virtual, Vatican City
Communication dans un congrès hal-03753541v1
Image document

Pragmatically Learning from Pedagogical Demonstrations in Multi-Goal Environments

Hugo Caselles-Dupré , Olivier Sigaud , Mohamed Chetouani
Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022), Nov 2022, New Orleans, United States
Communication dans un congrès hal-03828002v1

Selection-Expansion: A Unifying Framework for Motion-Planning and Diversity Search Algorithms

Alexandre Chenu , Nicolas Perrin-Gilbert , Stéphane Doncieux , Olivier Sigaud
30th International Conference on Artificial Neural Networks - ICANN 2021, Sep 2021, Bratislava, Slovakia. pp.568-579, ⟨10.1007/978-3-030-86380-7_46⟩
Communication dans un congrès hal-03404366v1

First-Order and Second-Order Variants of the Gradient Descent in a Unified Framework

Thomas Pierrot , Nicolas Perrin-Gilbert , Olivier Sigaud
30th International Conference on Artificial Neural Networks - ICANN 2021, Sep 2021, Bratislava, Slovakia. pp.197-208, ⟨10.1007/978-3-030-86340-1_16⟩
Communication dans un congrès hal-03404369v1
Image document

Grounding Language to Autonomously-Acquired Skills via Goal Generation

Ahmed Akakzia , Cédric Colas , Pierre-Yves Oudeyer , Mohamed Chetouani , Olivier Sigaud
ICLR 2021 - Ninth International Conference on Learning Representation, May 2021, Vienna / Virtual, Austria
Communication dans un congrès hal-03121146v1

Teaching a Robot with Unlabeled Instructions: The TICS Architecture

Anis Najar , Olivier Sigaud , Mohamed Chetouani
AAMAS 2021, May 2021, London (virtual), United Kingdom
Communication dans un congrès hal-03224574v1

PBCS: Efficient Exploration and Exploitation Using a Synergy Between Reinforcement Learning and Motion Planning

Guillaume Matheron , Nicolas Perrin , Olivier Sigaud
Artificial Neural Networks and Machine Learning – ICANN 2020, Sep 2020, Bratislava, Slovakia. pp.295-307, ⟨10.1007/978-3-030-61616-8_24⟩
Communication dans un congrès hal-03080918v1

Understanding Failures of Deterministic Actor-Critic with Continuous Action Spaces and Sparse Rewards

Guillaume Matheron , Nicolas Perrin , Olivier Sigaud
Artificial Neural Networks and Machine Learning – ICANN 2020, Sep 2020, Bratislava, Slovakia. pp.308-320, ⟨10.1007/978-3-030-61616-8_25⟩
Communication dans un congrès hal-03080925v1
Image document

Tirl: enriching actor-critic RL with non-expert human teachers and a trust model

Felix Rutard , Olivier Sigaud , Mohamed Chetouani
The 29th IEEE International Conference on Robot and Human Interactive Communication, RO-MAN, 2020, Napoli, Italy
Communication dans un congrès hal-03124262v1
Image document

CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning

Cédric Colas , Pierre Fournier , Olivier Sigaud , Mohamed Chetouani , Pierre-Yves Oudeyer
ICML 2019 - Thirty-sixth International Conference on Machine Learning, Jun 2019, Long Beach, United States
Communication dans un congrès hal-01934921v2

Learning Compositional Neural Programs with Recursive Tree Search and Planning

Thomas Pierrot , Guillaume Ligner , Scott Reed , Olivier Sigaud , Nicolas Perrin
Advances in Neural Information Processing Systems 32 (NeurIPS 2019), Dec 2019, Vancouver, Canada
Communication dans un congrès hal-03080949v1
Image document

CEM-RL: Combining evolutionary and gradient-based methods for policy search

Aloïs Pourchot , Olivier Sigaud
7th International Conference on Learning Representations, ICLR 2019, May 2019, New Orleans, United States
Communication dans un congrès hal-03753707v1
Image document

A Hitchhiker's Guide to Statistical Comparisons of Reinforcement Learning Algorithms

Cédric Colas , Olivier Sigaud , Pierre-Yves Oudeyer
ICLR Worskhop on Reproducibility, May 2019, Nouvelle-Orléans, United States
Communication dans un congrès hal-02369859v1
Image document

Modélisation des stratégies de génération de choix variables chez la souris

Marwen Belkaid , Jérémie Naudé , Philippe Faure , Olivier Sigaud
Conférence Nationale en Intelligence Artificielle, Jul 2019, Toulouse, France
Communication dans un congrès hal-02328815v1
Image document

GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms

Cédric Colas , Olivier Sigaud , Pierre-Yves Oudeyer
International Conference on Machine Learning (ICML), Jul 2018, Stockholm, Sweden
Communication dans un congrès hal-01890151v1
Image document

Unsupervised Learning of Goal Spaces for Intrinsically Motivated Goal Exploration

Alexandre Péré , Sébastien Forestier , Olivier Sigaud , Pierre-Yves Oudeyer
ICLR2018 - 6th International Conference on Learning Representations, Apr 2018, Vancouver, Canada
Communication dans un congrès hal-01891758v1
Image document

Tensor based knowledge transfer across skill categories for robot control

Chenyang Zhao , Timothy Hospedales , Freek Stulp , Olivier Sigaud
International Joint Conference in Artificial Intelligence (IJCAI), 2017, Melbourne, Australia. pp.1-7, ⟨10.24963/ijcai.2017/484⟩
Communication dans un congrès hal-03124263v1
Image document

Combining artificial curiosity and tutor guidance for environment exploration

Pierre Fournier , Olivier Sigaud , Mohamed Chetouani
Workshop on Behavior Adaptation, Interaction and Learning for Assistive Robotics at IEEE RO-MAN 2017, Aug 2017, Lisbon, Portugal
Communication dans un congrès hal-01581363v1

GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms

Cédric Colas , Olivier Sigaud , Pierre-Yves Oudeyer
Journées Francophones sur la Planification, la Décision et l'Apprentissage pour la conduite de systèmes (JFPDA 2018), Jul 2017, Nancy, France
Communication dans un congrès hal-01840576v1
Image document

The Successor Representation as a model of behavioural flexibility

Alexis Ducarouge , Olivier Sigaud
Journées Francophones sur la Planification, la Décision et l'Apprentissage pour la conduite de systèmes (JFPDA 2017), Jul 2017, Caen, France
Communication dans un congrès hal-01576352v1
Image document

Efficient Reinforcement Learning for Humanoid Whole-Body Control

Ryan Lober , Vincent Padois , Olivier Sigaud
IEEE-RAS International Conference on Humanoid Robots, Nov 2016, Cancun, Mexico
Communication dans un congrès hal-01377831v1
Image document

Training a robot with evaluative feedback and unlabeled guidance signals

Anis Najar , Olivier Sigaud , Mohamed Chetouani
RO-MAN, 2016, New York, United States. pp.261-266, ⟨10.1109/ROMAN.2016.7745140⟩
Communication dans un congrès hal-03124264v1

Socially Guided XCS

Anis Najar , Olivier Sigaud , Mohamed Chetouani
GECCO Companion '15 Proceedings of the Companion Publication of the 2015 Annual Conference on Genetic and Evolutionary Computation, Jul 2015, Madrid, Spain. pp.1021-1028, ⟨10.1145/2739482.2768452⟩
Communication dans un congrès hal-02423004v1

Social-Task Learning for HRI

Anis Najar , Olivier Sigaud , Mohamed Chetouani
International Conference on Social Robotics, Oct 2015, Paris, France. pp.472-481, ⟨10.1007/978-3-319-25554-5_47⟩
Communication dans un congrès hal-02422990v1
Image document

Socially guided xcs: using teaching signals to boost learning

Anis Najar , Olivier Sigaud , Mohamed Chetouani
GECCO (Companion), 2015, Madrid, Spain. pp.1021-1028, ⟨10.1145/2739482.2768452⟩
Communication dans un congrès hal-03124265v1
Image document

Learning a Repertoire of Actions with Deep Neural Networks

Alain Droniou , Serena Ivaldi , Olivier Sigaud
Joint International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EpiRob), Oct 2014, Italy. 6 p
Communication dans un congrès hal-01065741v1
Image document

Multiple Task Optimization using Dynamical Movement Primitives for Whole-Body Reactive Control

Ryan Lober , Vincent Padois , Olivier Sigaud
IEEE-RAS International Conference on Humanoid Robots, Nov 2014, Madrid, Spain
Communication dans un congrès hal-01077753v1
Image document

Robot initiative increases the rhythm of interaction in a team learning task

Serena Ivaldi , Salvatore Anzalone , Woody Rousseau , Olivier Sigaud , Mohamed Chetouani
Timing in Human-Robot interaction, Workshop of the 9th ACM/IEEE Int. Conf. on Human-robot interaction - HRI, 2014, Bielefeld, Germany
Communication dans un congrès hal-03124266v1
Image document

Non-linear regression algorithms for motor skill acquisition: a comparison

Thibaut Munzer , Freek Stulp , Olivier Sigaud
9èmes Journées Francophones de Planification, Décision et Apprentissage, May 2014, Liège, Belgium
Communication dans un congrès hal-01090848v1

Learning object names through shared attention

Woody Rousseau , Salvatore Anzalone , Mohamed Chetouani , Olivier Sigaud , Serena Ivaldi
IROS - Int. Workshop on Developmental Social Robotics, 2013, Madrid, Spain. pp.1-6
Communication dans un congrès hal-03124267v1

Learning Compact Parameterized Skills with a Single Regression

Freek Stulp , Gennaro Raiola , Antoine Hoarau , Serena Ivaldi , Olivier Sigaud
IEEE-RAS International Conference on Humanoid Robots, 2013, Atlanta, United States
Communication dans un congrès hal-00922135v1
Image document

Learning to recognize objects through curiosity-driven manipulation with the iCub humanoid robot

Sao Mai Nguyen , Serena Ivaldi , Natalia Lyubova , Alain Droniou , Damien Gerardeaux-Viret
Joint IEEE International Conference Developmental Learning and Epigenetic Robotics (ICDL-EPIROB), Aug 2013, Osaka, Japan. pp.1--8, ⟨10.1109/DevLrn.2013.6652525⟩
Communication dans un congrès hal-00919674v1

Cues for making a humanoid child more ''human-like'' during social learning tasks

Serena Ivaldi , Salvatore Anzalone , Woody Rousseau , Olivier Sigaud , Mohamed Chetouani
IROS - Int. Workshop Towards social humanoid robots: what makes interaction human-like?, 2013, Tokyo, Japan. pp.1-6
Communication dans un congrès hal-03124268v1

Policy Improvement: Between Black-Box Optimization and Episodic Reinforcement Learning

Freek Stulp , Olivier Sigaud
Journées Francophones Planification, Décision, et Apprentissage pour la conduite de systèmes, 2013, Lille, France
Communication dans un congrès hal-00922133v1
Image document

Gated Autoencoders with Tied Input Weights

Alain Droniou , Olivier Sigaud
International Conference on Machine Learning, 2013, United States
Communication dans un congrès hal-00817035v1
Image document

Which Temporal Difference Learning algorithm best reproduces dopamine activity in a multi-choice task?

Jean Bellot , Olivier Sigaud , Mehdi Khamassi
International Conference on Simulation of Adaptive Behaviour (SAB 2012), Aug 2012, Odense, Denmark. pp.289-298, ⟨10.1007/978-3-642-33093-3_29⟩
Communication dans un congrès hal-00731475v1
Image document

Autonomous Online Learning of Velocity Kinematics on the iCub: a Comparative Study

Alain Droniou , Serena Ivaldi , Vincent Padois , Olivier Sigaud
IEEE/RSJ International Conference on Intelligent Robots and Systems, Oct 2012, Vilamoura, Portugal. To appear
Communication dans un congrès hal-00719964v1

Towards fast and adaptive optimal control policies for robots: A direct policy search approach

Didier Marin , Olivier Sigaud
Robotica 2012, 2012, Guimaraes, Portugal. pp.21-26
Communication dans un congrès hal-00703755v1
Image document

Perception and human interaction for developmental learning of objects and affordances

Serena Ivaldi , Natalya Lyubova , Damien Gérardeaux-Viret , Alain Droniou , Salvatore Anzalone
Proc. of the 12th IEEE-RAS International Conference on Humanoid Robots - HUMANOIDS, Nov 2012, Santa Monica, United States. ⟨10.1109/HUMANOIDS.2012.6651528⟩
Communication dans un congrès hal-00755297v1
Image document

Comparaison expérimentale d'algorithmes de régression pour l'apprentissage de modèles cinématiques du robot humanoïde iCub

Alain Droniou , Serena Ivaldi , Olivier Sigaud
Conférence Francophone sur l'Apprentissage Automatique, May 2012, Nancy, France. pp.95-110
Communication dans un congrès hal-00719977v1
Image document

Comparaison expérimentale d'algorithmes de régression pour l'apprentissage de modèles cinématiques du robot humanoïde iCub

Alain Droniou , Serena Ivaldi , Olivier Sigaud
Conférence Francophone sur l'Apprentissage Automatique - CAp 2012, Laurent Bougrain, May 2012, Nancy, France. 16 p
Communication dans un congrès hal-00745471v1

Multimodal People Engagement with iCub

Salvatore Anzalone , Serena Ivaldi , Olivier Sigaud , Mohamed Chetouani
Biologically Inspired Cognitive Architectures, Oct 2012, Palermo, Italy. pp.59-64, ⟨10.1007/978-3-642-34274-5_16⟩
Communication dans un congrès hal-02423157v1
Image document

Reaching optimally over the workspace: a machine learning approach

Didier Marin , Olivier Sigaud
The Fourth IEEE RAS/EMBS International Conference on Biomedical Robotics and Biomechatronics, Jun 2012, Roma, Italy. pp.1128-1133, ⟨10.1109/BioRob.2012.6290743⟩
Communication dans un congrès hal-00743371v1
Image document

Learning Velocity Kinematics: Experimental Comparison of On-line Regression Algorithms

Alain Droniou , Serena Ivaldi , Patrick Stalph , Martin Butz , Olivier Sigaud
Robotica, Apr 2012, Guimaraes, Portugal. pp.15-20
Communication dans un congrès hal-00719975v1

Social Coordination Assessment: Distinguishing between Shape and Timing

Serena Ivaldi , Damien Gerardeaux-Viret , Alain Droniou , Salvatore Anzalone , Olivier Sigaud
Multimodal Pattern Recognition of Social Signals in Human-Computer-Interaction, Nov 2012, Tsukuba, Japan. pp.9-18, ⟨10.1007/978-3-642-37081-6_2⟩
Communication dans un congrès hal-02423165v1
Image document

Adaptation de la matrice de covariance pour l'apprentissage par renforcement direct

Freek Stulp , Olivier Sigaud
Journées Francophones sur la planification, la décision et l'apprentissage pour le contrôle des systèmes - JFPDA 2012, May 2012, Villers-lès-Nancy, France. 12 p
Communication dans un congrès hal-00736310v1

Path Integral Policy Improvement with Covariance Matrix Adaptation

Freek Stulp , Olivier Sigaud
Proceedings of the 29th International Conference on Machine Learning (ICML), Jun 2012, Edinbourg, United Kingdom. pp.0-0
Communication dans un congrès hal-00789391v1

Learning Cost-Efficient Control Policies with XCSF: Generalization Capabilities and Further Improvement

Didier Marin , Jérémie Decock , Lionel Rigoux , Olivier Sigaud
GECCO 2011, 2011, Dublin, Ireland. pp.1235-1242
Communication dans un congrès hal-00703760v1
Image document

Learning the velocity kinematics of iCub for model-based control: XCSF versus LWPR

Guillaume Sicard , Camille Salaün , Serena Ivaldi , Vincent Padois , Olivier Sigaud
11th IEEE-RAS International Conference on Humanoid Robots - Humanoids 2011, Oct 2011, Bled, Slovenia. pp.570--575, ⟨10.1109/Humanoids.2011.6100818⟩
Communication dans un congrès hal-00624056v2

Apprentissage de politiques efficaces avec XCSF et CEPS

Didier Marin , Jérémie Decock , Lionel Rigoux , Olivier Sigaud
JFPDA 2011, 2011, Rouen, France. pp.298-310
Communication dans un congrès hal-00703774v1
Image document

XCSF with local deletion: preventing detrimental forgetting

Martin Butz , Olivier Sigaud
International Workshop on Learning Classifier Systems, 2011, Dublin, Ireland. pp.1-8
Communication dans un congrès hal-03124269v1
Image document

Texdyna: hierarchical reinforcement learning in factored mdps

Olga Kozlova , Olivier Sigaud , Christophe Meyer
From Animals to Animats: Proceedings of the 11th International Conference on Adaptive Behaviour (SAB 2010), 2010, Paris, France. pp.489-500
Communication dans un congrès hal-03124272v1

Apprentissage par renforcement appliqué au contrôle moteur : reproduction du principe d'isochronie

Didier Marin , Olivier Sigaud
JFPDA 2010, 2010, Besançon, France. pp.1-11
Communication dans un congrès hal-00703784v1
Image document

Characterization of a least effort user-centered trajectory for sit- to-stand assistance user-centered trajectory for sit-to-stand assistance

Viviane Pasqui , Ludovic Saint-Bauzel , Olivier Sigaud
Symposium on Dynamics modeling and interaction control in virtual and real environments, 2010, Budapest, Hungary. pp.197-204
Communication dans un congrès hal-03124271v1
Image document

A comparative study: function approximation with lwpr and xcsf

Patrick Stalph , Jeremy Rubinsztajn , Olivier Sigaud , Martin Butz
IWLCS 2010, 2010, Portland, United States. pp.1-8, ⟨10.1145/1830761.1830818⟩
Communication dans un congrès hal-03124270v1
Image document

Control of redundant robots using learned models: an operational space control approach

Camille Salaün , Vincent Padois , Olivier Sigaud
IEEE/RSJ International Conference on Intelligent Robots and Systems, Oct 2009, Saint Louis, United States. pp.878--885, ⟨10.1109/IROS.2009.5354438⟩
Communication dans un congrès hal-00624322v1

Transfer of knowledge for a climbing virtual human: a reinforcement learning approach

Benoit Libeau , Alain Micaelli , Olivier Sigaud
Proceedings IEEE International Conference on Robotics and Automation, 2009, Kobe, Japan. pp.2119-2124
Communication dans un congrès hal-03124273v1

Automated discovery of options in factored reinforcement learning

Olga Kozlova , Olivier Sigaud , Christophe Meyer
Proceedings of the ICML/UAI/COLT Workshop on Abstraction in Reinforcement Learning, 2009, Montreal, Canada. pp.24-29
Communication dans un congrès hal-03124274v1

Considering Unseen States as Impossible in Factored Reinforcement Learning

Olga Kozlova , Olivier Sigaud , Pierre-Henri Wuillemin , Christophe Meyer
European Conference on Machine Learning, Sep 2009, Bled, Slovenia. pp.721-735, ⟨10.1007/978-3-642-04180-8_64⟩
Communication dans un congrès hal-01296687v1

Compacting a rule base into an and/or diagram for game ai

Samuel Manier , Olivier Sigaud
GAMEON, 2008, Valencia, Spain. pp.77-85
Communication dans un congrès hal-03124275v1

Exploiting Additive Structure in Factored MDPs for Reinforcement Learning

Thomas Degris , Olivier Sigaud , Pierre-Henri Wuillemin
European Workshop on Reinforcement Learning, Jun 2008, Villeneuve d’Ascq, France. pp.15-26, ⟨10.1007/978-3-540-89722-4_2⟩
Communication dans un congrès hal-01302178v1
Image document

Un modéle computationnel de l'automatisation motrice

Lionel Rigoux , Olivier Sigaud
Deuxième conférence française de Neurosciences Computationnelles, "Neurocomp08", Oct 2008, Marseille, France
Communication dans un congrès hal-00331620v1
Image document

Learning postures through sensorimotor training: a human simulation case study

Belonia Gabalda , Lionel Rigoux , Olivier Sigaud
Proceedings of the Seventh International Conference on Epigenetic Robotics, 2007, Rutgers, Piscataway, NJ, Unknown Region. pp.29-36
Communication dans un congrès hal-03124276v1

Apprentissage par renforcement exploitant la structure additive des MDP factorisés

Thomas Degris , Olivier Sigaud , Pierre-Henri Wuillemin
JFPDA 2007 - 2e Journées Francophones Planification, Décision, Apprentissage pour la conduite de système, Jul 2007, Grenoble, France. pp.49-60
Communication dans un congrès hal-01305984v1

Learning the Structure of Factored Markov Decision Processes in Reinforcement Learning Problems

Thomas Degris , Olivier Sigaud , Pierre-Henri Wuillemin
The 23rd International Conference on Machine Learning, Jun 2006, Pittsburgh, Pennsylvania, United States. pp.257-264, ⟨10.1145/1143844.1143877⟩
Communication dans un congrès hal-01336925v1

Apprentissage de la structure des processus de décision markoviens factorisés pour l'apprentissage par renforcement

Thomas Degris , Olivier Sigaud , Pierre-Henri Wuillemin
JFPDA 2006 - 1ères Journées Francophones sur la Planification, Décision, Apprentissage pour la conduite de systèmes, May 2006, Toulouse, France. pp.89-96
Communication dans un congrès hal-01336934v1

Chi-square Tests Driven Method for Learning the Structure of Factored MDPs

Thomas Degris , Olivier Sigaud , Pierre-Henri Wuillemin
The 22nd conference on Uncertainty in Artificial Intelligence, Jul 2006, Massachusetts Institute of Technology, Cambridge, MA, United States. pp.122-129
Communication dans un congrès hal-01351133v1

GACS, an Evolutionary Approach to the Spatial Coordination of Agents

Fabien Flacher , Olivier Sigaud
AAMAS 2005 - 4th international joint conference on Autonomous agents and multiagent systems, Jul 2005, Utrecht, Netherlands. pp.1109-1110, ⟨10.1145/1082473.1082647⟩
Communication dans un congrès hal-01416706v1
Image document

ATNoSFERES revisited

Samuel Landau , Olivier Sigaud , Marc Schoenauer
GECCO 2005 - 7th annual conference on Genetic and Evolutionary Computation Conference, , ACM SIGEVO, Jun 2005, Washington DC, United States. pp.1867-1874, ⟨10.1145/1068009.1068324⟩
Communication dans un congrès inria-00000158v1

Towards a Reinforcement Learning Module for Navigation in Video Games

Thierry Gourdin , Olivier Sigaud
ECML 2005 Workshop on Reinforcement Learning in Non-Stationary Environments, Oct 2005, Porto, Portugal. pp.1-12
Communication dans un congrès hal-01491687v1

Anticipation of Periodic Movements in Real Time 3D Environments

Vincent Labbé , Olivier Sigaud , Philippe Codognet
ABiALS 2004 - 2nd Workshop of Anticipatory Behavior in Adaptive Learning Systems, Jul 2004, Los Angeles, CA, United States. pp.51-61
Communication dans un congrès hal-01498522v1

Using XCS to build adaptive agents

Zahia Guessoum , Lilia Rejeb , Olivier Sigaud
4th Symposium on Adaptive Agents and Multi-Agent Systems (AAMAS-4), AISB convention, Mar 2004, Leeds, United Kingdom. pp.101-106
Communication dans un congrès hal-01496303v1

Improving MACS thanks to a comparison with 2TBNs

Thierry Gourdin , Olivier Sigaud , Pierre-Henri Wuillemin
GECCO 2004 - Genetic and Evolutionary Computation Conference, Jun 2004, Seattle, WA, United States. pp.810-823, ⟨10.1007/978-3-540-24855-2_95⟩
Communication dans un congrès hal-01501406v1

BASC, a Bottom-up Approach to automated design of Spatial Coordination

Fabien Flacher , Olivier Sigaud
SAB 2004 - 8th International Conference on Simulation of Adaptive Behavior, Jul 2004, Los Angeles, CA, United States. pp.435-444
Communication dans un congrès hal-01498529v1

A Michigan style architecture for learning finite state controllers: a first step

Samuel Landau , Olivier Sigaud
7th International Workshop on Learning Classifier Systems, Jun 2004, Seattle, WA, United States
Communication dans un congrès hal-01498518v1

Designing Efficient Exploration with MACS: Modules and Function Approximation

Pierre Gérard , Olivier Sigaud
Genetic and Evolutionary Computation Conference 2003 (GECCO03), Jul 2003, Chicago, IL, United States. pp.1882-1893, ⟨10.1007/3-540-45110-2_85⟩
Communication dans un congrès hal-01532220v1

Apprentissage par renforcement indirect dans les systèmes de classeurs

Olivier Sigaud , Pierre Gérard
Troisièmes Journées Nationales sur Processus Décisionnel de Markov et Intelligence Artificielle - PDMIA’03, 2003, Caen, France
Communication dans un congrès hal-01532006v1
Image document

An Experimental Comparison between ATNoSFERES and ACS

Samuel Landau , Olivier Sigaud , Sébastien Picault , Pierre Gérard
6th International Workshop on Learning Classifier Systems (IWLCS'2003), 2003, Chicago, United States. pp.144-160
Communication dans un congrès hal-00860490v1
Image document

A Comparison between ATNoSFERES and XCSM

Samuel Landau , Sébastien Picault , Olivier Sigaud , Pierre Gérard
GECCO 2002: Genetic and Evolutionary Computation Conference, Jul 2002, New York, United States. pp.926-933
Communication dans un congrès hal-00860423v1

Spatial Coordination through Social Potential Fields and Genetic Algorithms

Fabien Flacher , Olivier Sigaud
7th International Conference on Simulation of Adaptive Behavior, 2002, Edimburg, United Kingdom. pp.389-390
Communication dans un congrès hal-01548174v1
Image document

Further Comparison between ATNoSFERES and XCSM

Samuel Landau , Sébastien Picault , Olivier Sigaud , Pierre Gérard
IWLCS 2002 - 5th International Workshop on Learning Classifier Systems, Sep 2002, Granada, Spain. pp.99-117, ⟨10.1007/978-3-540-40029-5_7⟩
Communication dans un congrès hal-00860450v1

Adding a Generalization Mechanism to YACS

Pierre Gérard , Olivier Sigaud
GECCO 2001 - 3rd Annual Conference on Genetic and Evolutionary Computation, Jul 2001, San Francisco, CA, United States. pp.951-957
Communication dans un congrès hal-01571789v1

Using Classifier Systems as Adaptive Expert Systems for Control

Olivier Sigaud , Pierre Gérard
IWLCS 2000 - 3rd International Workshop on Learning Classifier Systems, Sep 2000, Paris, France. pp.138-157, ⟨10.1007/3-540-44640-0_10⟩
Communication dans un congrès hal-01571784v1

YACS : Combining Anticipation and Dynamic Programming in CLassifier Systems

Pierre Gérard , Olivier Sigaud
IWLCS 2000 - 3rd International Workshop on Learning Classifier Systems, Sep 2000, Paris, France. pp.52-69, ⟨10.1007/3-540-44640-0_5⟩
Communication dans un congrès hal-01571787v1

The use of roles in a multiagent adaptive simulation

Olivier Sigaud , Pierre Gérard
14th European Conference in Artificial Intelligence, Workshop on Balancing reactivity and Social Deliberation in Multiagent Systems, Aug 2000, Berlin, Germany
Communication dans un congrès hal-01573199v1

Markov Decision Processes in Artificial Intelligence

Olivier Sigaud , Olivier Buffet
Olivier Sigaud and Olivier Buffet. ISTE Ltd and John Wiley & Sons Inc, pp.455, 2010, 978-1-84821-167-4
Ouvrages inria-00432735v1

Processus décisionnels de Markov en intelligence artificielle

Olivier Sigaud , Olivier Buffet
Lavoisier - Hermes Science Publications, 1 - principes généraux et applications, pp.258, 2008, IC2 - informatique et systèmes d'information, Bernard Dubuisson - Jean-Charles Pomerol, 978-2746220577
Ouvrages inria-00326864v1

Processus décisionnels de Markov en intelligence artificielle

Olivier Buffet , Olivier Sigaud
Lavoisier - Hermes Science Publications, 2 - méthodes avancées et applications, pp.256, 2008, IC2 - informatique et systèmes d'information, Bernard Dubuisson - Jean-Charles Pomerol, 978-2746220584
Ouvrages inria-00326860v1

Anticipatory Behavior in Adaptive Learning Systems

Martin V. Butz , Olivier Sigaud , Pierre Gérard
Springer, 2684, 2003, Lecture Notes in Computer Science, ⟨10.1007/b11711⟩
Ouvrages hal-01532241v1

Artifical Intelligence and Pattern Recognition, Vision, Learning

Isabelle Bloch , Régis Clouard , Marinette Revenu , Olivier Sigaud
Springer. A Guided Tour of Artificial Intelligence Research (P. Marquis, O. Papini, H. Prade, Eds), III, Springer, pp.337-364, 2020
Chapitre d'ouvrage hal-02288075v1

7 : Intelligence artificielle et reconnaissance des formes, vision, apprentissage

Isabelle Bloch , Régis Clouard , Marinette Revenu , Olivier Sigaud
Panorama de l’intelligence artificielle - Ses bases méthodologiques ses développements - Volume 3 (P. Marquis, O. Papini, H. Prade, eds.), Cépaduès, pp.1165-1195, 2014
Chapitre d'ouvrage hal-02286463v1

Intelligence artificielle et reconnaissance des formes, vision, apprentissage pour la robotique

Isabelle Bloch , Régis Clouard , Marinette Revenu , Olivier Sigaud
L'Intelligence Artificielle : Frontières et Applications, Volume 3, série : Panorama de l'Intelligence Artificielle, Editions CEPADUES, 30 pp, 2014, 9782364930438
Chapitre d'ouvrage hal-00995039v1
Image document

Learning Forward Models for the Operational Space Control of Redundant Robots

Camille Salaün , Vincent Padois , Olivier Sigaud
Olivier Sigaud and Jan Peters. From Motor Learning to Interaction Learning in Robots, Springer, pp.169--192, 2010, Studies in Computational Intelligence, volume 264, ⟨10.1007/978-3-642-05181-4_8⟩
Chapitre d'ouvrage hal-00586453v1
Image document

A Two-Level Model of Anticipation-Based Motor Learning for Whole Body Motion

Camille Salaün , Vincent Padois , Olivier Sigaud
Giovanni Pezzulo, Martin V. Butz, Olivier Sigaud and Gianluca Baldassarre. Anticipatory Behavior in Adaptive Learning Systems: From Psychological Theories to Artificial Cognitive System, Springer, pp.229--246, 2009, Lecture Notes in Computer Science Volume 5499, ⟨10.1007/978-3-642-02565-5_13⟩
Chapitre d'ouvrage hal-00624103v1

Anticipations, Brains, Individual and Social Behavior: An Introduction to Anticipatory Systems

Martin Butz , Olivier Sigaud , Giovanni Pezzulo , Gianluca Baldassarre
Anticipatory Behavior in Adaptive Learning Systems: From Brains to Individual and Social Behavior, 4520, Springer-Verlag, pp.1-18, 2007, Lecture Notes in Computer Science, 978-3-540-74261-6. ⟨10.1007/978-3-540-74262-3_1⟩
Chapitre d'ouvrage hal-01311570v1

Internal Models and Anticipations in Adaptive Learning Systems

Martin V. Butz , Olivier Sigaud , Pierre Gérard
Anticipatory Behavior in Adaptive Learning Systems, 2684, Springer, pp.86-109, 2003, Lecture Notes in Computer Science, ⟨10.1007/978-3-540-45002-3_6⟩
Chapitre d'ouvrage hal-01532236v1

Anticipatory Behavior: Exploiting Knowledge about the Future to Improve Current Behavior

Martin V. Butz , Olivier Sigaud , Pierre Gérard
Anticipatory Behavior in Adaptive Learning Systems, 2684, Springer, pp.1-10, 2003, Lecture Notes in Computer Science, ⟨10.1007/978-3-540-45002-3_1⟩
Chapitre d'ouvrage hal-01532240v1

Vers une approche dynamique de la sélection de l'action

Olivier Sigaud , Fabien Flacher
Approche dynamique de la cognition artificielle, Hermès, pp.163-178, 2002
Chapitre d'ouvrage hal-01548147v1

Being Reactive by Exchanging Roles: an Empirical Study

Olivier Sigaud , Pierre Gérard
Balancing reactivity and Social Deliberation in Multiagent Systems, 2103, Springer-Verlag, pp.150-172, 2000, Lecture Notes in Computer Science, ⟨10.1007/3-540-44568-4_10⟩
Chapitre d'ouvrage hal-01571768v1

Contribution au problème de la sélection de l'action en environnement partiellement observable

Olivier Sigaud , Pierre Gérard
Intelligence Artificielle Située, Hermès, pp.129-146, 1999
Chapitre d'ouvrage hal-01574465v1
Image document

Co-Apprentissage Humain-Machine : Cas d’Étude en Acquisition de Compétences Motrices

Vaynee Sungeelee , Antoine Loriette , Olivier Sigaud , Baptiste Caramiaux
2023
Pré-publication, Document de travail hal-04014981v1
Image document

Language-Conditioned Goal Generation: a New Approach to Language Grounding in RL

Cédric Colas , Ahmed Akakzia , Pierre-Yves Oudeyer , Mohamed Chetouani , Olivier Sigaud
2021
Pré-publication, Document de travail hal-03099887v1
Image document

Selection-Expansion: A Unifying Framework for Motion-Planning and Diversity Search Algorithms

Alexandre Chenu , Nicolas Perrin-Gilbert , Stephane Doncieux , Olivier Sigaud
2021
Pré-publication, Document de travail hal-03196479v1
Image document

Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Survey

Cédric Colas , Tristan Karch , Olivier Sigaud , Pierre-Yves Oudeyer
2021
Pré-publication, Document de travail hal-03099891v1

Learning Compositional Neural Programs for Continuous Control

Thomas Pierrot , Nicolas Perrin , Feryal Behbahani , Alexandre Laterre , Olivier Sigaud
2020
Pré-publication, Document de travail hal-03083161v1
Image document

DREAM Architecture: a Developmental Approach to Open-Ended Learning in Robotics

Stephane Doncieux , Nicolas Bredeche , Léni Kenneth Le Goff , Benoît Girard , Alexandre Coninx
2020
Pré-publication, Document de travail hal-02562103v1

QD-RL: Efficient Mixing of Quality and Diversity in Reinforcement Learning

Geoffrey Cideron , Thomas Pierrot , Nicolas Perrin , Karim Beguir , Olivier Sigaud
2020
Pré-publication, Document de travail hal-03083159v1

First-order and second-order variants of the gradient descent in a unified framework

Thomas Pierrot , Nicolas Perrin , Olivier Sigaud
2019
Pré-publication, Document de travail hal-02397757v1

Importance mixing: Improving sample reuse in evolutionary policy search methods

Aloïs Pourchot , Nicolas Perrin , Olivier Sigaud
2019
Pré-publication, Document de travail hal-02397754v1
Image document

How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experiments

Cédric Colas , Olivier Sigaud , Pierre-Yves Oudeyer
2018
Pré-publication, Document de travail hal-01890154v1
Image document

Gated networks: an inventory

Olivier Sigaud , Clément Masson , David Filliat , Freek Stulp
2016
Pré-publication, Document de travail hal-01313601v1
Image document

Variance Modulated Task Prioritization in Whole-Body Control

Ryan Lober , Vincent Padois , Olivier Sigaud
2015
Pré-publication, Document de travail hal-01180011v1
Image document

Policy Improvement Methods: Between Black-Box Optimization and Episodic Reinforcement Learning

Freek Stulp , Olivier Sigaud
2012
Pré-publication, Document de travail hal-00738463v1