A voir également
- Profil
- Publications -----------------------------
- GDR Robotique : GT8
- GDR Robotique : GT8 (6 9 2012)
Publications
Titre : Professeur.e
Adresse : 4 place Jussieu, CC 173, 75252 Paris cedex 05
Email : sigaud(at)isir.upmc.fr
Equipe : AMAC (AMAC)
Publications classées par catégorie - Publications classées par date
Telecharger toutes les publications : format Bibtex - format CSV
Liste des publications (150).
[2020ACLI4732] - Fournier, P. and Colas, C. and Chetouani, M. and Sigaud, O. (2020). CLIC: Curriculum Learning and Imitation for object Control in non-rewarding environments.
IEEE Transactions on Cognitive and Developmental Systems. to appear.
[ HTTP | BIB ]
[2020ACLI4819] - Najar, A. and Sigaud, O. and Chetouani, M. (2020). Interactively shaping robot behaviour with unlabeled human instructions..
Autonomous Agents and Multi-Agent Systems volume. Vol 34 No 2 Pages 35.
[ DOI | BIB ]
[2020ACTI4852] - Rutard, F. and Sigaud, O. and Chetouani, M. (2020). TIRL: Enriching Actor-Critic RL with Non-Expert Human Teachers and a Trust Model.
The 29th IEEE International Conference on Robot and Human Interactive Communication, RO-MAN. Pages 604-611. Napoli, Italy.
[ HTTP | DOI | BIB ]
[2020AP4820] - Doncieux, S. and Bredèche, N. and LeGoff, L. and Girard, B. and Coninx, A. and Sigaud, O. and Khamassi, M. and Díaz-Rodríguez, N. and Filliat, D. and Hospedales, T. and Eiben, A. and Duro, R. (2020). DREAM Architecture: a Developmental Approach to Open-Ended Learning in Robotics.
Published : HAL preprint..
[ PDF | HTTP | BIB ]
[2019ACTI4733] - Colas, C. and Fournier, P. and Sigaud, O. and Chetouani, M. and Oudeyer, P.-Y. (2019). CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning.
Proceedings of the 36th International Conference on Machine Learning, PMLR. Vol 97 Pages 1331-1340,.
[ BIB ]
[2018ACLI4549] - Romano, F. and Nava, G. and Azad, M. and ÄŒamernik, J. and Dafarra, S. and Dermy, O. and Latella, C. and Lazzaroni, M. and Lober, R. and Lorenzini, M. and Pucci, D. and Sigaud, O. and Traversaro, S. and Babic, J. and Ivaldi, S. and Mistry, M. and Padois, V. and Nori, F. (2018). The CoDyCo Project Achievements and Beyond: TowardHuman Aware Whole-Body Controllers for Physical Human Robot Interaction.
IEEE Robotics and Automation Letters. Vol 3 No 1 Pages 516-523.
[ HTTP | BIB ]
[2018ACLI4637] - Lehir, N. and Laflaquière, A. and Sigaud, O. (2018). Identification of Invariant Sensorimotor Structures as a Prerequisite for the Discovery of Objects.
Frontiers in Robotics and AI. Vol 5 Pages 70.
[ HTTP | DOI | BIB ]
[2018ACLI4635] - Doncieux, S. and Filliat, D. and Diaz-Rodriguez, N. and Hospedales, T. and Duro, R. and Coninx, A. and Roijers, D.M. and Girard, B. and Perrin, N. and Sigaud, O. (2018). Open-Ended Learning: A Conceptual Framework Based on Representational Redescription.
Frontiers in Neurorobotics. Vol 12 Pages 59.
[ PDF | HTTP | DOI | BIB ]
[2018ACTI4588] - Péré, A. and Forestier, S. and Sigaud, O. and Oudeyer, P.-Y. (2018). Unsupervised Learning of Goal Spaces for Intrinsically Motivated Goal Exploration.
ICLR. Pages 1-26.
[ HTTP | BIB ]
[2018ACTI4589] - Colas, C. and Sigaud, O. and Oudeyer, P.-Y. (2018). GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms.
ICML. Pages 1-13.
[ HTTP | BIB ]
[2018RPT4590] - Sigaud, O. and Stulp, F. (2018). Policy Search in Continuous Action Domains: an Overview.
Sorbonne Université. https://arxiv.org/pdf/1803.04706.pdf.
[ BIB ]
[2017ACLI4591] - Peternel, L. and Sigaud, O. and Babic, J. (2017). Unifying Speed-Accuracy Trade-Off and Cost-Benefit Trade-Off in Human Reaching Movements.
Frontiers in Human Neuroscience. Vol 11 Pages 65.
[ PDF | BIB ]
[2017ACTI4087] - Zhao, C. and Hospedales, T. M. and Stulp, F. and Sigaud, O. (2017). Tensor Based Knowledge Transfer Across Skill Categories for Robot Control.
International Joint Conference in Artificial Intelligence (IJCAI). Pages 1-7.
[ PDF | BIB ]
[2017ACTI4550] - Fournier, P. and Sigaud, O. and Chetouani, M. (2017). Combining artificial curiosity and tutor guidance for environment exploration.
Workshop on Behavior Adaptation, Interaction and Learning for Assistive Robotics at IEEE RO-MAN 2017. Pages 1-8.
[ HTTP | BIB ]
[2017ACTN4082] - Ducarouge, A. and Sigaud, O. (2017). The Successor Representation as a model of behavioural flexibility.
Proceedings JFPDA. Pages 1-16.
[ PDF | BIB ]
[2016ACLI3716] - Sigaud, O. and Droniou, A. (2016). Towards Deep Developmental Learning.
IEEE Transactions on Cognitive and Developmental Systems. Vol 8 No 2 Pages 99-114.
[ PDF | DOI | BIB ]
[2016ACTI3709] - Najar, A. and Sigaud, O. and Chetouani, M. (2016). Training a Robot with Evaluative Feedback and Unlabeled Guidance Signals .
RO-MAN. Pages 261-266.
[ PDF | BIB ]
[2016ACTI3764] - Lober, R. and Padois, V. and Sigaud, O. (2016). Efficient Reinforcement Learning for Humanoid Whole-Body Control.
Proceedings of the IEEE-RAS International Conference on Humanoid Robots. Pages 1-6. Cancun, Mexico.
[ PDF | HTTP | DOI | BIB ]
[2016ACTN3726] - De Froissard de Broissia, Arnaud and Sigaud, Olivier (2016). Actor-critic versus direct policy search: a comparison based on sample complexity.
Proceedings JFPDA. Pages 1-9. Grenoble.
[ PDF | BIB ]
[2015ACLI3230] - Droniou, A. and Ivaldi, S. and Sigaud, O. (2015). Deep Unsupervised Network for Multimodal Perception, Representation and Classification.
Robotics and Autonomous Systems. Vol 71 Pages 83-98.
[ HTTP | BIB ]
[2015ACLI3134] - Lesaint, F. and Sigaud, O. and Clark, J.J. and Flagel, S.B. and Khamassi, M. (2015). Experimental predictions drawn from a computational model of sign-trackers and goal-trackers.
Journal of Physiology - Paris. Vol 109 No 1-3 Pages 78-86.
[ PDF | HTTP | DOI | BIB ]
[2015ACLI3575] - Stulp, F. and Sigaud, O. (2015). Many regression algorithms, one unified model: A review.
Neural Networks. Vol 69 Pages 60-79.
[ HTTP | DOI | BIB ]
[2015ACTI3475] - Najar, A. and Sigaud, O. and Chetouani, M. (2015). Socially Guided XCS: Using Teaching Signals to Boost Learning.
GECCO (Companion). Pages 1021--1028.
[ PDF | BIB ]
[2015ACTI3521] - Lober, Ryan and Padois, Vincent and Sigaud, Olivier (2015). Variance Modulated Task Prioritization in Whole-Body Control.
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems. Pages 3944-3949.
[ HTTP | DOI | BIB ]
[2015ACTI3598] - Najar, A. and Sigaud, O. and Chetouani, M. (2015). Social-Task Learning for HRI.
ICSR. Pages 472-481. Paris.
[ PDF | BIB ]
[2014ACLI3188] - Lesaint, F. and Sigaud, O. and Khamassi, M. (2014). Accounting for Negative Automaintenance in Pigeons: A Dual Learning Systems Approach and Factored Representations.
PLoS ONE. Vol 9 No 10 Pages e111050.
[ PDF | HTTP | DOI | BIB ]
[2014ACLI2906] - Ivaldi, S. and Nguyen, S.M. and Lyubova, N. and Droniou, A. and Padois, V. and Filliat, D. and Oudeyer, P.-Y. and Sigaud, O. (2014). Object learning through active exploration.
IEEE Transactions on Autonomous Mental Development. Vol 6 No 1 Pages 56 - 72 .
[ PDF | HTTP | DOI | BIB ]
[2014ACLI2994] - Ivaldi, S. and Anzalone, S.M. and Rousseau, W. and Sigaud, O. and Chetouani, M. (2014). Robot initiative in a team learning task increases the rhythm of interaction but not the perceived engagement.
Frontiers in Neurorobotics. Vol 8 No 5 Pages 1-23.
[ HTTP | BIB ]
[2014ACLI3016] - Lesaint, F. and Sigaud, O. and Flagel, S.B. and Robinson, T.E. and Khamassi, M. (2014). Modelling Individual Differences in the Form of Pavlovian Conditioned Approach Responses: A Dual Learning Systems Approach with Factored Representations.
PLoS Computational Biology. Vol 10 No 2 Pages e1003466.
[ PDF | HTTP | DOI | BIB ]
[2014ACTI3011] - Ivaldi, S. and Anzalone, S. and Rousseau, W. and Sigaud, O. and Chetouani, M. (2014). Robot initiative increases the rhythm of interaction in a team learning task.
Proc. Timing in Human-Robot interaction, Workshop of the 9th ACM/IEEE Int. Conf. on Human-robot interaction - HRI. Pages 1-4.
[ PS | PDF | BIB ]
[2014ACTI3189] - Lober, R. and Padois, V. and Sigaud, O. (2014). Multiple Task Optimization using Dynamical Movement Primitives for Whole-Body Reactive Control.
2014 IEEE-RAS International Conference on Humanoid Robots. Pages 1-6.
[ PDF | BIB ]
[2014ACTI3185] - Droniou, Alain and Ivaldi, Serena and Sigaud, Olivier (2014). Learning a Repertoire of Actions with Deep Neural Networks.
Proceedings of ICDL-EpiRob. Pages --.
[ PDF | BIB ]
[2014ACTN3084] - Munzer, T. and Stulp, F. and Sigaud, O. (2014). Non-linear regression algorithms for motor skill acquisition: a comparison.
Proceedings JFPDA. Pages 1-16.
[ PDF | BIB ]
[2014COM3418] - Lesaint, F. and Sigaud, O. and Khamassi, M. (2014). A model of negative automaintenance in pigeons: Dual learning and factored representations.
Society for Neuroscience Annual Meeting. Washington, DC, USA. Poster.
[ BIB ]
[2014COM3419] - Lesaint, F. and Sigaud, O. and Khamassi, M. (2014). Accounting for negative automaintenance in pigeons: A dual learning systems approach and factored representations.
Fourth Symposium on Biology of Decision Making (SBDM 2014). Paris, France. Poster.
[ HTTP | BIB ]
[2013ACLI2758] - Sigaud, O. and Butz, M. and Pezzulo, G. and Herbort, O. (2013). The anticipatory construction of reality as a central concern for psychology and robotics.
New Ideas in Psychology. Vol 31 Pages 217-220.
[ PDF | DOI | BIB ]
[2013ACLI2890] - Stulp, F. and Sigaud, O. (2013). Robot Skill Learning: From Reinforcement Learning to Evolution Strategies.
Paladyn Journal of Behavioral Robotics. Vol 4 No 1 Pages 49-61.
[ HTTP | DOI | BIB ]
[2013ACLN2754] - Marin, D. and Rigoux, L. and Sigaud, O. (2013). Apprentissage et optimisation de politiques pour un bras articulé actionné par des muscles.
Revue d'Intelligence Artificielle. Vol 27 (2) Pages 195-215. .
[ PDF | BIB ]
[2013ACLN2757] - Sigaud, O. and Stulp, F. (2013). Adaptation de la matrice de covariance pour l'apprentissage par renforcement direct.
Revue d'Intelligence Artificielle. Vol 27 (2) Pages 243-263. .
[ PDF | BIB ]
[2013ACTI2837] - Droniou, A. and Sigaud, O. (2013). Gated Autoencoders with Tied Input Weights.
Proceedings International Conference on Machine Learning. Pages x.
[ PDF | BIB ]
[2013ACTI2863] - Nguyen, S-M. and Ivaldi, S. and Lyubova, N. and Droniou, A. and Gerardeaux-Viret, D. and Filliat, D. and Padois, V. and Sigaud, O. and Oudeyer, P-Y. (2013). Learning to recognize objects through curiosity-driven manipulation with the iCub humanoid robot.
Proc. IEEE Int. Conf. Development and Learning and on Epigenetic Robotics - ICDL-EPIROB. Pages 1--8.
[ PDF | HTTP | DOI | BIB ]
[2013ACTI2891] - Stulp, F. and Raiola, G. and Hoarau, A. and Ivaldi, S. and Sigaud, O. (2013). Learning Compact Parameterized Skills with a Single Regression.
Proc. IEEE-RAS International Conference on Humanoid RObots - HUMANOIDS. Pages 1-7.
[ PDF | BIB ]
[2013ACTI2963] - Rousseau, W. and Anzalone, S.M. and Chetouani, M. and Sigaud, O. and Ivaldi, S. (2013). Learning object names through shared attention.
IROS - Int. Workshop on Developmental Social Robotics. Pages 1-6.
[ BIB ]
[2013ACTI2964] - Ivaldi, S. and Anzalone, S.M. and Rousseau, W. and Sigaud, O. and Chetouani, M. (2013). Cues for making a humanoid child more ''human-like'' during social learning tasks.
IROS - Int. Workshop Towards social humanoid robots: what makes interaction human-like?. Pages 1-6.
[ BIB ]
[2013ACTN2859] - Stulp, F. and Sigaud, O. (2013). Policy Improvement: Between Black-Box Optimization and Episodic Reinforcement Learning.
Proceedings JFPDA. Pages 1-15.
[ PDF | BIB ]
[2013COM2852] - Khamassi, M. and Bellot, J. and Sigaud, O. and Girard, B. (2013). Which temporal difference learning algorithm best reproduces dopamine activity in multi-choice task?.
11th meeting of the French Neuroscience Society. Lyon-Grenoble, France. poster P2.214.
[ BIB ]
[2013COM2868] - Bellot, J and Sigaud, O. and Girard, B. and Khamassi, M. (2013). Which temporal difference learning algorithm best reproduces dopamine activity in multi-choice task?.
Third Symposium on Biology of Decision Making (SBDM 2013). Paris. Poster #5.
[ BIB ]
[2013COM2882] - Bellot, J. and Khamassi, M. and Sigaud, O. and Girard, B. (2013). Which Temporal Difference learning algorithm best reproduces dopamine activity in a multi-choice task?.
Twenty Second Annual Computational Neuroscience Meeting: CNS*2013. Paris, France. poster P144.
[ HTTP | BIB ]
[2013COM2975] - Lesaint, F. and Sigaud, O. and Flagel, S. and Robinson, T. and Khamassi, M. (2013). Modelling individual differences in rats using a dual learning systems approach and factored representations.
First International Interdisciplinary Reinforcement Learning and Decision Making Conference Princeton University. Princeton, USA. Poster.
[ HTTP | BIB ]
[2013COM2976] - Lesaint, F. and Sigaud, O. and Khamassi, M. (2013). Modelling individual differences observed in rats using a dual learning systems approach and factored representations.
Third Symposium on Biology of Decision Making (SBDM 2013). Paris, France. Poster.
[ HTTP | BIB ]
[2013COM2977] - Lesaint, F. and Sigaud, O. and Flagel, S. and Robinson, T. and Khamassi, M. (2013). Modelling individual differences in rats using a dual learning systems approach and factored representations.
Fifth International Motivational and Cognitive Control Meeting. ICM Paris.
[ HTTP | BIB ]
[2012ACLI2414] - Stalph, P. and Rubinsztajn, J. and Sigaud, O. and Butz, M. (2012). Function approximation with LWPR and XCSF: a comparative study.
Evolutionary Intelligence. Vol 5 Pages 103-116.
[ HTTP | BIB ]
[2012ACLI2415] - Butz, M. and Sigaud, O. (2012). XCSF with local deletion: preventing detrimental forgetting.
Evolutionary Intelligence. Vol 5 Pages 117 - 127.
[ HTTP | BIB ]
[2012ACLI2416] - Marin, D. and Sigaud, O. (2012). A machine learning approach to reaching tasks.
Computer Methods in Biomechanics and Biomedical Engineering. Vol 15 No sup1 Pages 151-152.
[ PDF | HTTP | DOI | BIB ]
[2012ACLI2471] - Ivaldi, S. and Sigaud, O. and Berret, B. and Nori, F. (2012). From Humans to Humanoids: the Optimal Control Framework.
Paladyn Journal of Behavioral Robotics. Vol 3 No 2 Pages 75-91.
[ PDF | HTTP | BIB ]
[2012ACTI2354] - Marin, D. and Sigaud, O. (2012). Towards fast and adaptive optimal control policies for robots: A direct policy search approach.
Proceedings Robotica'2012. Pages 21-26. Guimaraes, Portugal.
[ PDF | BIB ]
[2012ACTI2355] - Droniou, A. and Ivaldi, S. and Stalph, P. and Butz, M. and Sigaud, O. (2012). Learning Velocity Kinematics: Experimental Comparison of On-line Regression Algorithms.
Proceedings Robotica. Pages 15-20.
[ PDF | HTTP | BIB ]
[2012ACTI2399] - Bellot, J. and Sigaud, O. and Khamassi, M. (2012). Which Temporal Difference Learning algorithm best reproduces dopamine activity in a multi-choice task?.
From Animals to Animats: Proceedings of the Twelfth International Conference on Adaptive Behaviour (SAB 2012), Ziemke, T., Balkenius, C., Hallam, J. (Eds), Springer, publisher. Vol 7426/2012 Pages 289-298. Odense, Denmark. BEST PAPER AWARD.
[ PDF | HTTP | DOI | BIB ]
[2012ACTI2525] - Anzalone, S. M. and Ivaldi, S. and Sigaud, O. and Chetouani, M. (2012). Multimodal people engagement with iCub.
Annual International Conference on Biologically Inspired Cognitive Architectures, Springer, publisher. Pages 59-65. Palermo, Italy.
[ PDF | BIB ]
[2012ACTI2395] - Marin, D. and Sigaud, O. (2012). Reaching optimally over the workspace: a machine learning approach.
2012 4th IEEE RAS & EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob). Pages 1128-1133.
[ PDF | HTTP | DOI | BIB ]
[2012ACTI2408] - Stulp, F. and Sigaud, O. (2012). Path Integral Policy Improvement with Covariance Matrix Adaptation.
Proceedings ICML. Pages 1-8. Edinburgh, Scotland.
[ PDF | BIB ]
[2012ACTI2454] - Droniou, A. and Ivaldi, S. and Padois, V. and Sigaud, O (2012). Autonomous Online Learning of Velocity Kinematics on the iCub: a Comparative Study.
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems - IROS. Pages 3577-3582. Vilamoura, Portugal.
[ PDF | HTTP | DOI | BIB ]
[2012ACTI2527] - Ivaldi, S. and Lyubova, N. and Gérardeaux-Viret, D. and Droniou, A. and Anzalone, S. M. and Chetouani, M. and Filliat, D. and Sigaud, O. (2012). Perception and human interaction for developmental learning of objects and affordances.
Proc. of the 12th IEEE-RAS International Conference on Humanoid Robots - HUMANOIDS. Pages 1-8.
[ PDF | BIB ]
[2012ACTN2387] - Droniou, A. and Ivaldi, S. and Sigaud, O. (2012). Comparaison expérimentale d'algorithmes de régression pour l'apprentissage de modèles cinématiques du robot humanoïde iCub.
Conférence Francophone sur l'Apprentissage Automatique (Cap). Pages 95-110.
[ PDF | HTTP | BIB ]
[2012ACTN2398] - Stulp, F. and Sigaud, O. (2012). Adaptation de la matrice de covariance pour l'apprentissage par renforcement direct.
Proceedings JFPDA . Pages 1-12.
[ PDF | BIB ]
[2012ACTN2684] - Bellot, J. and Sigaud, O. and Roesch, M. R. and Schoenbaum, G. and Girard, B and Khamassi, M. (2012). Dopamine neurons activity in a multi-choice task: reward prediction error or value function?.
Proceedings of the French Computational Neuroscience NeuroComp/KEOpS\'12 workshop. Pages 1-7. Bordeaux, France.
[ PDF | HTTP | BIB ]
[2012COM2510] - Ivaldi, S. and Lyubova, N. and Gérardeaux-Viret, D. and Droniou, A. and Anzalone, S. M. and Chetouani, M. and Filliat, D. and Sigaud, O. (2012). A cognitive architecture for developmental learning of objects and affordances: perception and human interaction aspects.
IEEE Ro-man Workshop on Developmental and bio-inspired approaches for social cognitive robotics. Paris, France.
[ PDF | BIB ]
[2012COM3423] - Bellot, J. and Sigaud, O. and Khamassi, M. (2012). Which Temporal Difference Learning algorithm best reproduces dopamine activity in a multi-choice task?.
Fourth Robotics and Neuroscience Days. Paris, France. Poster.
[ BIB ]
[2012COM3424] - Bellot, J. and Sigaud, O. and Khamassi, M. (2012). Which Temporal Difference Learning algorithm best reproduces dopamine activity in a multi-choice task?.
Second Symposium on Biology of Decision Making (SBDM 2012). Paris, France. Poster.
[ HTTP | BIB ]
[2011ACLI2117] - Sigaud, O. and Salaun, C. and Padois, V. (2011). On-line regression algorithms for learning mechanical models of robots: a survey.
Robotics and Autonomous Systems, Elsevier, publisher. Vol 59 No 12 Pages 1115-1129.
[ HTTP | DOI | BIB ]
[2011ACTI1946] - Butz, M. and Sigaud, O. (2011). XCSF with Local Deletion: Preventing Detrimental Forgetting.
Proceedings International Workshop on Learning Classifier Systems, ACM Press, publisher. Pages 1-8.
[ PDF | BIB ]
[2011ACTI1945] - Marin, D. and Decock, J. and Rigoux, L. and Sigaud, O. (2011). Learning Cost-Efficient Control Policies with XCSF: Generalization Capabilities and Further Improvement.
Proceedings of the 13th annual conference on Genetic and evolutionary computation (GECCO'11), ACM Press, publisher. Pages 1235--1242.
[ PDF | BIB ]
[2011ACTI2063] - Sicard, G. and Salaun, C. and Ivaldi, S. and Padois, V. and Sigaud, O. (2011). Learning the velocity kinematics of iCub for model-based control: XCSF versus LWPR.
Proceedings of the 11th IEEE-RAS International Conference on Humanoid Robots - HUMANOIDS. Pages 570 -- 575. Bled, Slovenia.
[ HTTP | DOI | BIB ]
[2011ACTN1978] - Marin, D. and Decock, J. and Rigoux, L. and Sigaud, O. (2011). Apprentissage de politiques efficaces avec XCSF et CEPS.
Sixièmes journées francophones MFI/JFPDA, GREYC Caen, publisher. Pages 298-310. Rouen.
[ PDF | BIB ]
[2010COS1467] - Salaun, C. and Padois, V. and Sigaud, O. (2010). Learning Forward Models for the Operational Space Control of Redundant Robots.
From Motor Learning to Interaction Learning in Robots, Springer, publisher. Vol 264 Pages 169-192.
[ HTTP | DOI | BIB ]
[2010COS1550] - Sigaud, O. and Garcia, F. (2010). Reinforcement Learning.
Markov Decision Processes in Artificial Intelligence, iste - Wiley, publisher. Pages 39 - 66.
[ PDF | BIB ]
[2010COS1551] - Degris, T. and Sigaud, O. (2010). Factored Markov Decision Processes.
Markov Decision Processes in Artificial Intelligence, iste - Wiley, publisher. Pages 99 - 125.
[ PDF | BIB ]
[2010COS1600] - Sigaud, O. and Peters, J. (2010). From Motor Learning to Interaction Learning in Robots.
From Motor Learning to Interaction Learning in Robots, Springer-Verlag, publisher. Vol 264 Pages 1-12.
[ PDF | BIB ]
[2010COS2540] - Sigaud, O. and Peters, J. (2010). From Motor Learning to Interaction Learning in Robots.
From Motor Learning to Interaction Learning in Robots.
[ BIB ]
[2010DO1549] - Sigaud, O. and Buffet, O. (2010). Markov Decision Processes in Artificial Intelligence.
, iSTE - Wiley, publisher.
[ BIB ]
[2010DO2717] - Peters, J. and Sigaud, O. (2010). From Motor Learning to Interaction Learning in Robots.
, Springer, publisher.
[ BIB ]
[2010INVN2056] - Sigaud, O. (2010). Apprentissage par Renforcement.
RFIA, RFIA, publisher. Caen. invited conference.
[ PDF | BIB ]
[2010ACTI1537] - Stalph, P. O. and Rubinsztajn, J. and Sigaud, O. and Butz, M. V. (2010). A Comparative Study: Function Approximation with LWPR and XCSF.
IWLCS 2010. Pages 1-8.
[ PDF | BIB ]
[2010ACTI1539] - Pasqui, V. and Saint-Bauzel, L. and Sigaud, O. (2010). Characterization of a least effort user-centered trajectory for sit-to-stand assistance User-centered trajectory for sit-to-stand assistance.
Symposium on Dynamics modeling and interaction control in virtual and real environments IUTAM. Pages 197-204.
[ PDF | BIB ]
[2010ACTI1599] - Kozlova, O. and Sigaud, O. and Meyer, C. (2010). TeXDYNA: Hierarchical Reinforcement Learning in Factored MDPs.
From Animals to Animats: Proceedings of the 11th International Conference on Adaptive Behaviour (SAB 2010), Springer, publisher. Pages 489-500 .
[ PDF | BIB ]
[2010ACTN1538] - Marin, D. and Sigaud, O. (2010). Apprentissage par renforcement appliqué au contrôle moteur : reproduction du principe d'isochronie.
proceedings JFPDA. Pages 1-10. Besançon.
[ PDF | BIB ]
[2010COM1917] - Rigoux, L. and Sigaud, O. and Terekhov, A. and Guigon, E. (2010). Movement duration as an emergent property of reward directed motor control.
Proc Advances in Computational Motor Control, Symposium at the Society for Neuroscience Conference (Todorov E, Shadmehr R, Kording K, organizers). San Diego, CA, USA.
[ PDF | BIB ]
[2009ACLN945] - Degris, T. and Sigaud, O. and Wuillemin, P.-H. (2009). Apprentissage par renforcement factorisé pour le comportement de personnages non joueurs .
Revue d'Intelligence Artificielle, Lavoisier, publisher. Vol 23 Pages 221-252.
[ PDF | BIB ]
[2009COS1013] - Sigaud , O. and Butz, M. V. and Kozlova, O. and Meyer, C. (2009). Anticipatory Learning Classifier Systems and Factored Reinforcement Learning.
LNAI 5499: Anticipatory Behavior in Adaptive Learning Systems: From Psychological Theories to Artificial Cognitive Systems, Springer, publisher. Pages 321-333.
[ PDF | BIB ]
[2009COS1468] - Salaun, C. and Padois, V. and Sigaud, O. (2009). A Two-Level Model of Anticipation-Based Motor Learning for Whole Body Motion.
Anticipatory Behavior in Adaptive Learning Systems, From Psychological Theories to Artificial Cognitive Systems, Springer, publisher. Vol 5499 Pages 229-246.
[ HTTP | DOI | BIB ]
[2009INVI2058] - Sigaud, O. (2009). A tutorial about Reinforcement Learning.
IAS-ISF Motor Days. Jerusalem. invited conference.
[ PDF | BIB ]
[2009INVN1853] - Pasqui, V. and Saint-Bauzel, L. and Sigaud, O. (2009). Une aide technique robotisée pour la mobilité des personnes âgées handicapées.
Congrès de la Société Française des Technologies pour l’Autonomie et de Gérontechnologie SFTAG. Université de Technologie de Troyes. invited conference.
[ BIB ]
[2009INVN2057] - Sigaud, O. (2009). Apprentissage en Robotique, pourquoi, comment ?.
Journées Nationales de la Recherche en Robotique. Sologne. invited conference.
[ PDF | BIB ]
[2009ACTI946] - Libeau, B. and Micaelli, A. and Sigaud, O. (2009). Transfer of Knowledge for a Climbing Virtual Human: A Reinforcement Learning Approach .
Proceedings IEEE International Conference on Robotics and Automation. Pages 2119-2124.
[ PDF | BIB ]
[2009ACTI997] - Kozlova, O. and Sigaud, O. and Meyer, C. (2009). Automated Discovery of Options in Factored Reinforcement Learning.
Proceedings of the ICML/UAI/COLT Workshop on Abstraction in Reinforcement Learning. Pages 24-29. Montreal, Canada.
[ PDF | BIB ]
[2009ACTI1020] - Kozlova, O. and Sigaud, O. and Wuillemin, P.-H. and Meyer, C. (2009). Considering Unseen States as Impossible in Factored Reinforcement Learning.
ECML PKDD 2009, Part I, LNAI 5781-0721 , Springer, publisher. Pages 721--735.
[ PDF | BIB ]
[2009ACTI1470] - Salaun, C. and Padois, V. and Sigaud, O. (2009). Control of redundant robots using learned models: an operational space control approach.
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems. Pages 878--885. Saint-Louis, USA.
[ HTTP | DOI | BIB ]
[2008ACLI440] - Landau, S. and Sigaud, O. (2008). A Comparison between ATNoSFERES and LCSs on non-Markov problems.
Information Sciences. Vol 178 Pages 4482-4500.
[ PDF | BIB ]
[2008COS840] - Sigaud, O. and Garcia, F. (2008). Apprentissage par renforcement.
Processus décisionnels de Markov en intelligence artificielle (volume 1), Lavoisier, publisher. Ch 2 Pages 53--88.
[ PDF | BIB ]
[2008COS841] - Degris, T. and Sigaud, O. (2008). Représentations factorisées.
Processus décisionnels de Markov en intelligence artificielle (volume 2), Lavoisier, publisher. Ch 2 Pages 51--79.
[ PDF | BIB ]
[2008DO842] - Sigaud, O. and Buffet, O. (2008). Processus décisionnels de Markov en intelligence artificielle (volume 1).
, Lavoisier, publisher.
[ PDF | BIB ]
[2008DO843] - Buffet, O. and Sigaud, O. (2008). Processus décisionnels de Markov en intelligence artificielle (volume 2).
, Lavoisier, publisher.
[ PDF | BIB ]
[2008ACTI826] - Degris, T. and Sigaud, O. and Wuillemin, P.-H. (2008). Exploiting Additive Structure in Factored MDPs for Reinforcement Learning.
Proceedings EWRL, Springer, LNAI 5323, publisher. Pages 15-26. Lille, France.
[ PDF | BIB ]
[2008ACTI1601] - Manier, S. and Sigaud, O. (2008). Compacting a Rule Base into an and/or Diagram for Game AI.
GAMEON. Pages 77-85.
[ PDF | BIB ]
[2008ACTN827] - Kozlova, O. and Sigaud, O. and Meyer, C. (2008). Apprentissage par renforcement hiérarchique dans les MDP factorisés.
Actes JFPDA. Pages 93-102. Metz, France.
[ PDF | BIB ]
[2008ACTN918] - Rigoux, L. and Sigaud, O. (2008). Un modèle computationnel de l'automatisation motrice.
Proceedings of the second french conference on Computational Neuroscience. Pages 152-157. Marseille.
[ PDF | BIB ]
[2007ACLI483] - Sigaud, O. and Wilson, S. W. (2007). Learning Classifier Systems: A Survey.
Journal of Soft Computing, Springer, publisher. Vol 11 No 11 Pages 1065-1078.
[ PDF | BIB ]
[2007ACLN474] - Sigaud, O. (2007). Les systèmes de classeurs : un état de l'art.
Revue d'Intelligence Artificielle, Hermès, publisher. Vol 21 Pages 75-106.
[ PDF | BIB ]
[2007COS739] - Butz, M.V. and Sigaud, O. and Pezzulo, G. and Baldassarre, G. (2007). Anticipations, Brains, Individual and Social Behavior: An Introduction to Anticipatory Systems .
Anticipatory Behavior in Adaptive Learning Systems : From Brains to Individual and Social Behavior , LNAI 4520, Springer, publisher. Pages 1-18. ISBN: 978-3-540-74261-6.
[ PDF | BIB ]
[2007DO738] - Butz, M.V. and Sigaud, O. and Pezzulo, G. and Baldassarre, G., editor(s) (2007). Anticipatory Behavior in Adaptive Learning Systems : From Brains to Individual and Social Behavior.
Anticipatory Behavior in Adaptive Learning Systems : From Brains to Individual and Social Behavior, LNAI 4520, Springer, publisher. ISBN: 978-3-540-74261-6.
[ BIB ]
[2007ACTI776] - Gabalda, B. and Rigoux, L. and Sigaud, O. (2007). Learning postures through sensorimotor training: a human simulation case study.
Proceedings of the Seventh International Conference on Epigenetic Robotics. Pages 29-36. Rutgers, Piscataway, NJ.
[ PDF | BIB ]
[2007ACTN782] - Degris, T. and Sigaud, O. and Wuillemin, P.-H. (2007). Apprentissage par renforcement exploitant la structure additive des MDP factorisés.
Actes de la conférence JFPDA'07. Pages 49-60. Grenoble.
[ PDF | BIB ]
[2007COM1436] - Durlin, R. and Salaun, C. and Sigaud, O. (2007). Apprentissage de la verticalisation sur un humain virtuel.
Journées Nationales de la Robotique Humanoïde. Montpellier, France.
[ PDF | BIB ]
[2006ACLN383] - Flacher, F. and Sigaud, O. (2006). GACS : une approche ascendante pour la coordination spatiale.
Revue d'Intelligence Artificielle, Hermès, publisher. Vol 20 No 1 Pages 7--29.
[ PDF | BIB ]
[2006DO344] - Charpillet, F. and Garcia, F. and Perny, P. and Sigaud, O. (2006). Décision et planification dans l'incertain.
, Hermès, publisher.
[ BIB ]
[2006ACTI348] - Degris, T. and Sigaud, O. and Wuillemin, P.-H. (2006). Chi-square Tests Driven Method for Learning the Structure of Factored MDPs.
Proceedings of the 22nd Conference on Uncertainty in Artificial Intelligence (UAI), AUAI Press, publisher. Pages 122--129. Massachusetts Institute of Technology Cambridge, MA, USA.
[ PDF | BIB ]
[2006ACTI349] - Degris, T. and Sigaud, O. and Wuillemin, P.-H. (2006). Learning the Structure of Factored Markov Decision Processes in Reinforcement Learning Problems.
Proceedings of the 23rd International Conference on Machine Learning (ICML), ACM, publisher. Pages 257--264. Pittsburgh, Pennsylvania.
[ PDF | BIB ]
[2006ACTN350] - Degris, T. and Sigaud, O. and Wuillemin, P.-H. (2006). Apprentissage de la structure des processus de décision markoviens factorisés pour l'apprentissage par renforcement.
Actes de la conférence JFPDA'06. Pages 89-96. Toulouse.
[ PDF | BIB ]
[2005ACLI414] - Gérard, P. and Meyer, J.-A. and Sigaud, O. (2005). Combining Latent Learning and Dynamic Programming in MACS.
European Journal of Operational Research, Elsevier, publisher. Vol 160 Pages 614--637.
[ PDF | BIB ]
[2005ACTI382] - Flacher, F. and Sigaud, O. (2005). GACS, an Evolutionary Approach to the Spatial Coordination of Agents.
Proceedings AAMAS 2005, ACM Press, publisher. Pages 1109-1110. Utrecht, The netherlands.
[ PDF | BIB ]
[2005ACTI391] - Gourdin, T. and Sigaud, O. (2005). Towards a Reinforcement Learning Module for Navigation in Video Games.
Proceedings of the ECML05 Workshop on Reinforcement Learning in Non-Stationary Environments. Pages 1-12. Porto, Portugal.
[ PDF | BIB ]
[2005ACTI441] - Landau,S. and Sigaud, O. and Schoenauer, M. (2005). ATNoSFERES revisited.
Proceedings of the Genetic and Evolutionary Computation Conference, GECCO-2005, ACM Press, publisher. Pages 1867-1874. Washington DC.
[ PDF | BIB ]
[2004ACLI347] - Degris, T. and Sigaud, O. and Wiener, S. I. and Arleo, A. (2004). Rapid response of head direction cells to reorienting visual cues: A computational model.
Neurocomputing, Elsevier, publisher. Vol 58-60C Pages 675-682.
[ PDF | BIB ]
[2004ACLN482] - Sigaud, O. and Gérard, P. (2004). Apprentissage par renforcement indirect dans les systèmes de classeurs.
JEDAI. Vol 1 Pages 1-12.
[ PDF | HTTP | BIB ]
[2004ACTI381] - Flacher, F. and Sigaud, O. (2004). BASC, a Bottom-up Approach to automated design of Spatial Coordination.
From Animals to Animats 8: Proceedings of the Eighth International Conference on Simulation of Adaptive Behavior, MIT Press, publisher. Pages 435-444. Cambridge, MA.
[ PDF | BIB ]
[2004ACTI396] - Guessoum, Z. and Rejeb, L. and Sigaud, O. (2004). Using XCS to build Adaptive Agents.
Proceedings of the Fourth Symposium on Adaptive Agents and Multi-Agent Systems (AAMAS-4), AISB convention. Pages 101--106. Leeds.
[ PDF | BIB ]
[2004ACTI434] - Labbé, V. and Sigaud, O. (2004). Anticipation of Periodic Movements in Real Time 3D Environments.
Proceedings of the Anticipatory Behavior in Adaptive Learning Systems (ABiALS) 2004 Workshop. Pages 1-8. Los Angeles, CA.
[ PDF | HTTP | BIB ]
[2004ACTI439] - Landau, S. and Sigaud, O. (2004). A Michigan style architecture for learning finite state controllers: a first step.
Proceedings of the Seventh International Workshop on Learning Classifier Systems. Pages 1-8. Seattle, WA.
[ BIB ]
[2004ACTI476] - Sigaud, O. and Gourdin, T. and Wuillemin, P.-H. (2004). Improving MACS thanks to a comparison with 2TBNs.
Proceedings of the Genetic and Evolutionary Computation Conference, GECCO'04, Springer, publisher. Pages 810--823.
[ PDF | BIB ]
[2004THDR473] - Sigaud, O. (2004). Comportements adaptatifs pour des agents dans des environnements informatiques complexes.
. Paris. These. Université Pierre et Marie Curie, Paris 6.
[ PDF | BIB ]
[2003ACLN380] - Flacher, F. and Sigaud, O. (2003). Coordination spatiale émergente par champs de potentiel.
Technique et Science Informatique, Hermès, publisher. Vol 22 No 2 Pages 171--195.
[ PDF | BIB ]
[2003COS342] - Butz, M. V. and Sigaud, O. and Gérard, P. (2003). Anticipatory Behavior: Exploiting Knowledge about the Future to Improve Current Behavior.
LNCS 2684 : Anticipatory Behavior in Adaptive Learning Systems, Springer-Verlag, publisher.
[ PDF | BIB ]
[2003COS343] - Butz, M. V. and Sigaud, O. and Gérard, P. (2003). Internal Models and Anticipations in Adaptive Learning Systems.
LNCS 2684 : Anticipatory Behavior in Adaptive Learning Systems, Springer-Verlag, publisher.
[ PDF | BIB ]
[2003COS438] - Landau, S. and Picault, S. and Sigaud, O. and Gérard, P. (2003). Further Comparison between ATNoSFERES and XCSM.
Learning Classifier Systems LNCS 2661, Springer-Verlag, publisher. Pages 99--117.
[ PS | BIB ]
[2003DO335] - Butz, M. V. and Sigaud, O. and Gérard, P., editor(s) (2003). LNCS 2684 : Anticipatory Behavior in Adaptive Learning Systems.
, Springer-Verlag, publisher.
[ BIB ]
[2003ACTI419] - Gérard, P. and Sigaud, O. (2003). Designing Efficient Exploration with MACS: Modules and Function Approximation.
Proceedings of the Genetic and Evolutionary Computation Conference 2003 (GECCO03), Springer-Verlag, publisher. Pages 1882--1893. Chicago, IL.
[ PDF | BIB ]
[2003ACTN481] - Sigaud, O. and Gérard, P. (2003). Apprentissage par renforcement indirect dans les systèmes de classeurs.
Actes des journées PDMIA. Pages 1-8. In french.
[ BIB ]
[2002ACLI420] - Gérard, P. and Stolzmann, W. and Sigaud, O. (2002). YACS : Yet a new Learning Classifier System using Anticipation..
Journal of Soft Computing, Springer, publisher. Vol 6 No 3-4 Pages 216--228.
[ PDF | BIB ]
[2002COS475] - Sigaud, O. and Flacher, F. (2002). Vers une approche dynamique de la sélection de l'action.
Approche dynamique de la cognition artificielle, Hermès, publisher. Pages 163--178. Paris, France.
[ PDF | BIB ]
[2002ACTI379] - Flacher, F. and Sigaud, O. (2002). Spatial Coordination through Social Potential Fields and Genetic Algorithms.
From Animals to Animats 7. Proceedings of the Seventh International Conference on Simulation of Adaptive Behavior, MIT Press, publisher. Pages 389--390.
[ PDF | BIB ]
[2002ACTI436] - Landau, S. and Picault, S. and Sigaud, O. and Gérard, P. (2002). A Comparison between ATNoSFERES and XCSM.
Proceedings of the Genetic and Evolutionary Computation Conference, GECCO 2002, Morgan Kaufmann, publisher. Pages 926--933. New York, NY.
[ PDF | BIB ]
[2002ACTI437] - Landau, S. and Picault, S. and Sigaud, O. and Gérard, P. (2002). Further Comparison between ATNoSFERES and XCSM.
IWLCS-02. Proceedings of the Fourth International Workshop on Learning Classifier Systems, Springer, publisher. Pages 1-8.
[ PS | BIB ]
[2001ACLN418] - Gérard, P. and Sigaud, O. (2001). Généralisation et apprentissage latent dans les systèmes de classeurs.
Extraction des Connaissances et Apprentissage, Hermès, publisher. Vol 1 No 3 Pages 87--114.
[ PDF | BIB ]
[2001COS479] - Sigaud, O. and Gérard, P. (2001). Using Classifier Systems as Adaptive Expert Systems for Control.
LNAI 1996 : Advances in Classifier Systems, Springer-Verlag, publisher. Pages 138--157.
[ PDF | BIB ]
[2001COS480] - Sigaud, O. and Gérard, P. (2001). Being Reactive by Exchanging Roles: an Empirical Study.
LNAI 2103 : Balancing reactivity and Social Deliberation in Multiagent Systems, Springer-Verlag, publisher. Pages 138--157.
[ PDF | BIB ]
[2001ACTI416] - Gérard, P. and Sigaud, O. (2001). Adding a Generalization Mechanism to YACS.
Proceedings of the Genetic and Evolutionary Computation Conference 2001 (GECCO01), Morgan Kaufmann, publisher. Pages 951--957. San Francisco, CA.
[ PDF | BIB ]
[2001ACTI417] - Gérard, P. and Sigaud, O. (2001). YACS : Combining Anticipation and Dynamic Programming in Classifier Systems.
LNAI 1996 : Advances in Classifier Systems, Springer, publisher. Pages 52--69.
[ PDF | BIB ]
[2000ACTI415] - Gérard, P. and Sigaud, O. (2000). Combining Anticipation and Dynamic Programming in Classifier Systems.
Proceedings of the Third International Workshop on Learning Classifier Systems. Pages 1-8.
[ PDF | BIB ]
[2000ACTI478] - Sigaud, O. and Gérard, P. (2000). The use of roles in a multiagent adaptive simulation.
Proceedings of the 14th European Conference in Artificial Intellligence, Workshop on Balancing reactivity and Social Deliberation in Multiagent Systems. Pages 150-172. Berlin, Germany.
[ PDF | BIB ]
[1999ACTN477] - Sigaud, O. and Gérard, P. (1999). Contribution au problème de la sélection de l'action en environnement partiellement observable.
Intelligence Artificielle Située, Hermès, publisher. Pages 129--146. Paris, France.
[ PDF | BIB ]
2020
[2020ACLI4732] - Fournier, P. and Colas, C. and Chetouani, M. and Sigaud, O. (2020). CLIC: Curriculum Learning and Imitation for object Control in non-rewarding environments.
IEEE Transactions on Cognitive and Developmental Systems. to appear.
[ HTTP | BIB ]
[2020ACLI4819] - Najar, A. and Sigaud, O. and Chetouani, M. (2020). Interactively shaping robot behaviour with unlabeled human instructions..
Autonomous Agents and Multi-Agent Systems volume. Vol 34 No 2 Pages 35.
[ DOI | BIB ]
[2020ACTI4852] - Rutard, F. and Sigaud, O. and Chetouani, M. (2020). TIRL: Enriching Actor-Critic RL with Non-Expert Human Teachers and a Trust Model.
The 29th IEEE International Conference on Robot and Human Interactive Communication, RO-MAN. Pages 604-611. Napoli, Italy.
[ HTTP | DOI | BIB ]
[2020AP4820] - Doncieux, S. and Bredèche, N. and LeGoff, L. and Girard, B. and Coninx, A. and Sigaud, O. and Khamassi, M. and Díaz-Rodríguez, N. and Filliat, D. and Hospedales, T. and Eiben, A. and Duro, R. (2020). DREAM Architecture: a Developmental Approach to Open-Ended Learning in Robotics.
Published : HAL preprint..
[ PDF | HTTP | BIB ]
2019
[2019ACTI4733] - Colas, C. and Fournier, P. and Sigaud, O. and Chetouani, M. and Oudeyer, P.-Y. (2019). CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning.
Proceedings of the 36th International Conference on Machine Learning, PMLR. Vol 97 Pages 1331-1340,.
[ BIB ]
2018
[2018ACLI4549] - Romano, F. and Nava, G. and Azad, M. and ÄŒamernik, J. and Dafarra, S. and Dermy, O. and Latella, C. and Lazzaroni, M. and Lober, R. and Lorenzini, M. and Pucci, D. and Sigaud, O. and Traversaro, S. and Babic, J. and Ivaldi, S. and Mistry, M. and Padois, V. and Nori, F. (2018). The CoDyCo Project Achievements and Beyond: TowardHuman Aware Whole-Body Controllers for Physical Human Robot Interaction.
IEEE Robotics and Automation Letters. Vol 3 No 1 Pages 516-523.
[ HTTP | BIB ]
[2018ACLI4637] - Lehir, N. and Laflaquière, A. and Sigaud, O. (2018). Identification of Invariant Sensorimotor Structures as a Prerequisite for the Discovery of Objects.
Frontiers in Robotics and AI. Vol 5 Pages 70.
[ HTTP | DOI | BIB ]
[2018ACLI4635] - Doncieux, S. and Filliat, D. and Diaz-Rodriguez, N. and Hospedales, T. and Duro, R. and Coninx, A. and Roijers, D.M. and Girard, B. and Perrin, N. and Sigaud, O. (2018). Open-Ended Learning: A Conceptual Framework Based on Representational Redescription.
Frontiers in Neurorobotics. Vol 12 Pages 59.
[ PDF | HTTP | DOI | BIB ]
[2018ACTI4588] - Péré, A. and Forestier, S. and Sigaud, O. and Oudeyer, P.-Y. (2018). Unsupervised Learning of Goal Spaces for Intrinsically Motivated Goal Exploration.
ICLR. Pages 1-26.
[ HTTP | BIB ]
[2018ACTI4589] - Colas, C. and Sigaud, O. and Oudeyer, P.-Y. (2018). GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms.
ICML. Pages 1-13.
[ HTTP | BIB ]
[2018RPT4590] - Sigaud, O. and Stulp, F. (2018). Policy Search in Continuous Action Domains: an Overview.
Sorbonne Université. https://arxiv.org/pdf/1803.04706.pdf.
[ BIB ]
2017
[2017ACLI4591] - Peternel, L. and Sigaud, O. and Babic, J. (2017). Unifying Speed-Accuracy Trade-Off and Cost-Benefit Trade-Off in Human Reaching Movements.
Frontiers in Human Neuroscience. Vol 11 Pages 65.
[ PDF | BIB ]
[2017ACTI4087] - Zhao, C. and Hospedales, T. M. and Stulp, F. and Sigaud, O. (2017). Tensor Based Knowledge Transfer Across Skill Categories for Robot Control.
International Joint Conference in Artificial Intelligence (IJCAI). Pages 1-7.
[ PDF | BIB ]
[2017ACTI4550] - Fournier, P. and Sigaud, O. and Chetouani, M. (2017). Combining artificial curiosity and tutor guidance for environment exploration.
Workshop on Behavior Adaptation, Interaction and Learning for Assistive Robotics at IEEE RO-MAN 2017. Pages 1-8.
[ HTTP | BIB ]
[2017ACTN4082] - Ducarouge, A. and Sigaud, O. (2017). The Successor Representation as a model of behavioural flexibility.
Proceedings JFPDA. Pages 1-16.
[ PDF | BIB ]
2016
[2016ACLI3716] - Sigaud, O. and Droniou, A. (2016). Towards Deep Developmental Learning.
IEEE Transactions on Cognitive and Developmental Systems. Vol 8 No 2 Pages 99-114.
[ PDF | DOI | BIB ]
[2016ACTI3709] - Najar, A. and Sigaud, O. and Chetouani, M. (2016). Training a Robot with Evaluative Feedback and Unlabeled Guidance Signals .
RO-MAN. Pages 261-266.
[ PDF | BIB ]
[2016ACTI3764] - Lober, R. and Padois, V. and Sigaud, O. (2016). Efficient Reinforcement Learning for Humanoid Whole-Body Control.
Proceedings of the IEEE-RAS International Conference on Humanoid Robots. Pages 1-6. Cancun, Mexico.
[ PDF | HTTP | DOI | BIB ]
[2016ACTN3726] - De Froissard de Broissia, Arnaud and Sigaud, Olivier (2016). Actor-critic versus direct policy search: a comparison based on sample complexity.
Proceedings JFPDA. Pages 1-9. Grenoble.
[ PDF | BIB ]
2015
[2015ACLI3230] - Droniou, A. and Ivaldi, S. and Sigaud, O. (2015). Deep Unsupervised Network for Multimodal Perception, Representation and Classification.
Robotics and Autonomous Systems. Vol 71 Pages 83-98.
[ HTTP | BIB ]
[2015ACLI3134] - Lesaint, F. and Sigaud, O. and Clark, J.J. and Flagel, S.B. and Khamassi, M. (2015). Experimental predictions drawn from a computational model of sign-trackers and goal-trackers.
Journal of Physiology - Paris. Vol 109 No 1-3 Pages 78-86.
[ PDF | HTTP | DOI | BIB ]
[2015ACLI3575] - Stulp, F. and Sigaud, O. (2015). Many regression algorithms, one unified model: A review.
Neural Networks. Vol 69 Pages 60-79.
[ HTTP | DOI | BIB ]
[2015ACTI3475] - Najar, A. and Sigaud, O. and Chetouani, M. (2015). Socially Guided XCS: Using Teaching Signals to Boost Learning.
GECCO (Companion). Pages 1021--1028.
[ PDF | BIB ]
[2015ACTI3521] - Lober, Ryan and Padois, Vincent and Sigaud, Olivier (2015). Variance Modulated Task Prioritization in Whole-Body Control.
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems. Pages 3944-3949.
[ HTTP | DOI | BIB ]
[2015ACTI3598] - Najar, A. and Sigaud, O. and Chetouani, M. (2015). Social-Task Learning for HRI.
ICSR. Pages 472-481. Paris.
[ PDF | BIB ]
2014
[2014ACLI3188] - Lesaint, F. and Sigaud, O. and Khamassi, M. (2014). Accounting for Negative Automaintenance in Pigeons: A Dual Learning Systems Approach and Factored Representations.
PLoS ONE. Vol 9 No 10 Pages e111050.
[ PDF | HTTP | DOI | BIB ]
[2014ACLI2906] - Ivaldi, S. and Nguyen, S.M. and Lyubova, N. and Droniou, A. and Padois, V. and Filliat, D. and Oudeyer, P.-Y. and Sigaud, O. (2014). Object learning through active exploration.
IEEE Transactions on Autonomous Mental Development. Vol 6 No 1 Pages 56 - 72 .
[ PDF | HTTP | DOI | BIB ]
[2014ACLI2994] - Ivaldi, S. and Anzalone, S.M. and Rousseau, W. and Sigaud, O. and Chetouani, M. (2014). Robot initiative in a team learning task increases the rhythm of interaction but not the perceived engagement.
Frontiers in Neurorobotics. Vol 8 No 5 Pages 1-23.
[ HTTP | BIB ]
[2014ACLI3016] - Lesaint, F. and Sigaud, O. and Flagel, S.B. and Robinson, T.E. and Khamassi, M. (2014). Modelling Individual Differences in the Form of Pavlovian Conditioned Approach Responses: A Dual Learning Systems Approach with Factored Representations.
PLoS Computational Biology. Vol 10 No 2 Pages e1003466.
[ PDF | HTTP | DOI | BIB ]
[2014ACTI3011] - Ivaldi, S. and Anzalone, S. and Rousseau, W. and Sigaud, O. and Chetouani, M. (2014). Robot initiative increases the rhythm of interaction in a team learning task.
Proc. Timing in Human-Robot interaction, Workshop of the 9th ACM/IEEE Int. Conf. on Human-robot interaction - HRI. Pages 1-4.
[ PS | PDF | BIB ]
[2014ACTI3189] - Lober, R. and Padois, V. and Sigaud, O. (2014). Multiple Task Optimization using Dynamical Movement Primitives for Whole-Body Reactive Control.
2014 IEEE-RAS International Conference on Humanoid Robots. Pages 1-6.
[ PDF | BIB ]
[2014ACTI3185] - Droniou, Alain and Ivaldi, Serena and Sigaud, Olivier (2014). Learning a Repertoire of Actions with Deep Neural Networks.
Proceedings of ICDL-EpiRob. Pages --.
[ PDF | BIB ]
[2014ACTN3084] - Munzer, T. and Stulp, F. and Sigaud, O. (2014). Non-linear regression algorithms for motor skill acquisition: a comparison.
Proceedings JFPDA. Pages 1-16.
[ PDF | BIB ]
[2014COM3418] - Lesaint, F. and Sigaud, O. and Khamassi, M. (2014). A model of negative automaintenance in pigeons: Dual learning and factored representations.
Society for Neuroscience Annual Meeting. Washington, DC, USA. Poster.
[ BIB ]
[2014COM3419] - Lesaint, F. and Sigaud, O. and Khamassi, M. (2014). Accounting for negative automaintenance in pigeons: A dual learning systems approach and factored representations.
Fourth Symposium on Biology of Decision Making (SBDM 2014). Paris, France. Poster.
[ HTTP | BIB ]
2013
[2013ACLI2758] - Sigaud, O. and Butz, M. and Pezzulo, G. and Herbort, O. (2013). The anticipatory construction of reality as a central concern for psychology and robotics.
New Ideas in Psychology. Vol 31 Pages 217-220.
[ PDF | DOI | BIB ]
[2013ACLI2890] - Stulp, F. and Sigaud, O. (2013). Robot Skill Learning: From Reinforcement Learning to Evolution Strategies.
Paladyn Journal of Behavioral Robotics. Vol 4 No 1 Pages 49-61.
[ HTTP | DOI | BIB ]
[2013ACLN2754] - Marin, D. and Rigoux, L. and Sigaud, O. (2013). Apprentissage et optimisation de politiques pour un bras articulé actionné par des muscles.
Revue d'Intelligence Artificielle. Vol 27 (2) Pages 195-215. .
[ PDF | BIB ]
[2013ACLN2757] - Sigaud, O. and Stulp, F. (2013). Adaptation de la matrice de covariance pour l'apprentissage par renforcement direct.
Revue d'Intelligence Artificielle. Vol 27 (2) Pages 243-263. .
[ PDF | BIB ]
[2013ACTI2837] - Droniou, A. and Sigaud, O. (2013). Gated Autoencoders with Tied Input Weights.
Proceedings International Conference on Machine Learning. Pages x.
[ PDF | BIB ]
[2013ACTI2863] - Nguyen, S-M. and Ivaldi, S. and Lyubova, N. and Droniou, A. and Gerardeaux-Viret, D. and Filliat, D. and Padois, V. and Sigaud, O. and Oudeyer, P-Y. (2013). Learning to recognize objects through curiosity-driven manipulation with the iCub humanoid robot.
Proc. IEEE Int. Conf. Development and Learning and on Epigenetic Robotics - ICDL-EPIROB. Pages 1--8.
[ PDF | HTTP | DOI | BIB ]
[2013ACTI2891] - Stulp, F. and Raiola, G. and Hoarau, A. and Ivaldi, S. and Sigaud, O. (2013). Learning Compact Parameterized Skills with a Single Regression.
Proc. IEEE-RAS International Conference on Humanoid RObots - HUMANOIDS. Pages 1-7.
[ PDF | BIB ]
[2013ACTI2963] - Rousseau, W. and Anzalone, S.M. and Chetouani, M. and Sigaud, O. and Ivaldi, S. (2013). Learning object names through shared attention.
IROS - Int. Workshop on Developmental Social Robotics. Pages 1-6.
[ BIB ]
[2013ACTI2964] - Ivaldi, S. and Anzalone, S.M. and Rousseau, W. and Sigaud, O. and Chetouani, M. (2013). Cues for making a humanoid child more ''human-like'' during social learning tasks.
IROS - Int. Workshop Towards social humanoid robots: what makes interaction human-like?. Pages 1-6.
[ BIB ]
[2013ACTN2859] - Stulp, F. and Sigaud, O. (2013). Policy Improvement: Between Black-Box Optimization and Episodic Reinforcement Learning.
Proceedings JFPDA. Pages 1-15.
[ PDF | BIB ]
[2013COM2852] - Khamassi, M. and Bellot, J. and Sigaud, O. and Girard, B. (2013). Which temporal difference learning algorithm best reproduces dopamine activity in multi-choice task?.
11th meeting of the French Neuroscience Society. Lyon-Grenoble, France. poster P2.214.
[ BIB ]
[2013COM2868] - Bellot, J and Sigaud, O. and Girard, B. and Khamassi, M. (2013). Which temporal difference learning algorithm best reproduces dopamine activity in multi-choice task?.
Third Symposium on Biology of Decision Making (SBDM 2013). Paris. Poster #5.
[ BIB ]
[2013COM2882] - Bellot, J. and Khamassi, M. and Sigaud, O. and Girard, B. (2013). Which Temporal Difference learning algorithm best reproduces dopamine activity in a multi-choice task?.
Twenty Second Annual Computational Neuroscience Meeting: CNS*2013. Paris, France. poster P144.
[ HTTP | BIB ]
[2013COM2975] - Lesaint, F. and Sigaud, O. and Flagel, S. and Robinson, T. and Khamassi, M. (2013). Modelling individual differences in rats using a dual learning systems approach and factored representations.
First International Interdisciplinary Reinforcement Learning and Decision Making Conference Princeton University. Princeton, USA. Poster.
[ HTTP | BIB ]
[2013COM2976] - Lesaint, F. and Sigaud, O. and Khamassi, M. (2013). Modelling individual differences observed in rats using a dual learning systems approach and factored representations.
Third Symposium on Biology of Decision Making (SBDM 2013). Paris, France. Poster.
[ HTTP | BIB ]
[2013COM2977] - Lesaint, F. and Sigaud, O. and Flagel, S. and Robinson, T. and Khamassi, M. (2013). Modelling individual differences in rats using a dual learning systems approach and factored representations.
Fifth International Motivational and Cognitive Control Meeting. ICM Paris.
[ HTTP | BIB ]
2012
[2012ACLI2414] - Stalph, P. and Rubinsztajn, J. and Sigaud, O. and Butz, M. (2012). Function approximation with LWPR and XCSF: a comparative study.
Evolutionary Intelligence. Vol 5 Pages 103-116.
[ HTTP | BIB ]
[2012ACLI2415] - Butz, M. and Sigaud, O. (2012). XCSF with local deletion: preventing detrimental forgetting.
Evolutionary Intelligence. Vol 5 Pages 117 - 127.
[ HTTP | BIB ]
[2012ACLI2416] - Marin, D. and Sigaud, O. (2012). A machine learning approach to reaching tasks.
Computer Methods in Biomechanics and Biomedical Engineering. Vol 15 No sup1 Pages 151-152.
[ PDF | HTTP | DOI | BIB ]
[2012ACLI2471] - Ivaldi, S. and Sigaud, O. and Berret, B. and Nori, F. (2012). From Humans to Humanoids: the Optimal Control Framework.
Paladyn Journal of Behavioral Robotics. Vol 3 No 2 Pages 75-91.
[ PDF | HTTP | BIB ]
[2012ACTI2354] - Marin, D. and Sigaud, O. (2012). Towards fast and adaptive optimal control policies for robots: A direct policy search approach.
Proceedings Robotica'2012. Pages 21-26. Guimaraes, Portugal.
[ PDF | BIB ]
[2012ACTI2355] - Droniou, A. and Ivaldi, S. and Stalph, P. and Butz, M. and Sigaud, O. (2012). Learning Velocity Kinematics: Experimental Comparison of On-line Regression Algorithms.
Proceedings Robotica. Pages 15-20.
[ PDF | HTTP | BIB ]
[2012ACTI2399] - Bellot, J. and Sigaud, O. and Khamassi, M. (2012). Which Temporal Difference Learning algorithm best reproduces dopamine activity in a multi-choice task?.
From Animals to Animats: Proceedings of the Twelfth International Conference on Adaptive Behaviour (SAB 2012), Ziemke, T., Balkenius, C., Hallam, J. (Eds), Springer, publisher. Vol 7426/2012 Pages 289-298. Odense, Denmark. BEST PAPER AWARD.
[ PDF | HTTP | DOI | BIB ]
[2012ACTI2525] - Anzalone, S. M. and Ivaldi, S. and Sigaud, O. and Chetouani, M. (2012). Multimodal people engagement with iCub.
Annual International Conference on Biologically Inspired Cognitive Architectures, Springer, publisher. Pages 59-65. Palermo, Italy.
[ PDF | BIB ]
[2012ACTI2395] - Marin, D. and Sigaud, O. (2012). Reaching optimally over the workspace: a machine learning approach.
2012 4th IEEE RAS & EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob). Pages 1128-1133.
[ PDF | HTTP | DOI | BIB ]
[2012ACTI2408] - Stulp, F. and Sigaud, O. (2012). Path Integral Policy Improvement with Covariance Matrix Adaptation.
Proceedings ICML. Pages 1-8. Edinburgh, Scotland.
[ PDF | BIB ]
[2012ACTI2454] - Droniou, A. and Ivaldi, S. and Padois, V. and Sigaud, O (2012). Autonomous Online Learning of Velocity Kinematics on the iCub: a Comparative Study.
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems - IROS. Pages 3577-3582. Vilamoura, Portugal.
[ PDF | HTTP | DOI | BIB ]
[2012ACTI2527] - Ivaldi, S. and Lyubova, N. and Gérardeaux-Viret, D. and Droniou, A. and Anzalone, S. M. and Chetouani, M. and Filliat, D. and Sigaud, O. (2012). Perception and human interaction for developmental learning of objects and affordances.
Proc. of the 12th IEEE-RAS International Conference on Humanoid Robots - HUMANOIDS. Pages 1-8.
[ PDF | BIB ]
[2012ACTN2387] - Droniou, A. and Ivaldi, S. and Sigaud, O. (2012). Comparaison expérimentale d'algorithmes de régression pour l'apprentissage de modèles cinématiques du robot humanoïde iCub.
Conférence Francophone sur l'Apprentissage Automatique (Cap). Pages 95-110.
[ PDF | HTTP | BIB ]
[2012ACTN2398] - Stulp, F. and Sigaud, O. (2012). Adaptation de la matrice de covariance pour l'apprentissage par renforcement direct.
Proceedings JFPDA . Pages 1-12.
[ PDF | BIB ]
[2012ACTN2684] - Bellot, J. and Sigaud, O. and Roesch, M. R. and Schoenbaum, G. and Girard, B and Khamassi, M. (2012). Dopamine neurons activity in a multi-choice task: reward prediction error or value function?.
Proceedings of the French Computational Neuroscience NeuroComp/KEOpS\'12 workshop. Pages 1-7. Bordeaux, France.
[ PDF | HTTP | BIB ]
[2012COM2510] - Ivaldi, S. and Lyubova, N. and Gérardeaux-Viret, D. and Droniou, A. and Anzalone, S. M. and Chetouani, M. and Filliat, D. and Sigaud, O. (2012). A cognitive architecture for developmental learning of objects and affordances: perception and human interaction aspects.
IEEE Ro-man Workshop on Developmental and bio-inspired approaches for social cognitive robotics. Paris, France.
[ PDF | BIB ]
[2012COM3423] - Bellot, J. and Sigaud, O. and Khamassi, M. (2012). Which Temporal Difference Learning algorithm best reproduces dopamine activity in a multi-choice task?.
Fourth Robotics and Neuroscience Days. Paris, France. Poster.
[ BIB ]
[2012COM3424] - Bellot, J. and Sigaud, O. and Khamassi, M. (2012). Which Temporal Difference Learning algorithm best reproduces dopamine activity in a multi-choice task?.
Second Symposium on Biology of Decision Making (SBDM 2012). Paris, France. Poster.
[ HTTP | BIB ]
2011
[2011ACLI2117] - Sigaud, O. and Salaun, C. and Padois, V. (2011). On-line regression algorithms for learning mechanical models of robots: a survey.
Robotics and Autonomous Systems, Elsevier, publisher. Vol 59 No 12 Pages 1115-1129.
[ HTTP | DOI | BIB ]
[2011ACTI1946] - Butz, M. and Sigaud, O. (2011). XCSF with Local Deletion: Preventing Detrimental Forgetting.
Proceedings International Workshop on Learning Classifier Systems, ACM Press, publisher. Pages 1-8.
[ PDF | BIB ]
[2011ACTI1945] - Marin, D. and Decock, J. and Rigoux, L. and Sigaud, O. (2011). Learning Cost-Efficient Control Policies with XCSF: Generalization Capabilities and Further Improvement.
Proceedings of the 13th annual conference on Genetic and evolutionary computation (GECCO'11), ACM Press, publisher. Pages 1235--1242.
[ PDF | BIB ]
[2011ACTI2063] - Sicard, G. and Salaun, C. and Ivaldi, S. and Padois, V. and Sigaud, O. (2011). Learning the velocity kinematics of iCub for model-based control: XCSF versus LWPR.
Proceedings of the 11th IEEE-RAS International Conference on Humanoid Robots - HUMANOIDS. Pages 570 -- 575. Bled, Slovenia.
[ HTTP | DOI | BIB ]
[2011ACTN1978] - Marin, D. and Decock, J. and Rigoux, L. and Sigaud, O. (2011). Apprentissage de politiques efficaces avec XCSF et CEPS.
Sixièmes journées francophones MFI/JFPDA, GREYC Caen, publisher. Pages 298-310. Rouen.
[ PDF | BIB ]
2010
[2010COS1467] - Salaun, C. and Padois, V. and Sigaud, O. (2010). Learning Forward Models for the Operational Space Control of Redundant Robots.
From Motor Learning to Interaction Learning in Robots, Springer, publisher. Vol 264 Pages 169-192.
[ HTTP | DOI | BIB ]
[2010COS1550] - Sigaud, O. and Garcia, F. (2010). Reinforcement Learning.
Markov Decision Processes in Artificial Intelligence, iste - Wiley, publisher. Pages 39 - 66.
[ PDF | BIB ]
[2010COS1551] - Degris, T. and Sigaud, O. (2010). Factored Markov Decision Processes.
Markov Decision Processes in Artificial Intelligence, iste - Wiley, publisher. Pages 99 - 125.
[ PDF | BIB ]
[2010COS1600] - Sigaud, O. and Peters, J. (2010). From Motor Learning to Interaction Learning in Robots.
From Motor Learning to Interaction Learning in Robots, Springer-Verlag, publisher. Vol 264 Pages 1-12.
[ PDF | BIB ]
[2010COS2540] - Sigaud, O. and Peters, J. (2010). From Motor Learning to Interaction Learning in Robots.
From Motor Learning to Interaction Learning in Robots.
[ BIB ]
[2010DO1549] - Sigaud, O. and Buffet, O. (2010). Markov Decision Processes in Artificial Intelligence.
, iSTE - Wiley, publisher.
[ BIB ]
[2010DO2717] - Peters, J. and Sigaud, O. (2010). From Motor Learning to Interaction Learning in Robots.
, Springer, publisher.
[ BIB ]
[2010INVN2056] - Sigaud, O. (2010). Apprentissage par Renforcement.
RFIA, RFIA, publisher. Caen. invited conference.
[ PDF | BIB ]
[2010ACTI1537] - Stalph, P. O. and Rubinsztajn, J. and Sigaud, O. and Butz, M. V. (2010). A Comparative Study: Function Approximation with LWPR and XCSF.
IWLCS 2010. Pages 1-8.
[ PDF | BIB ]
[2010ACTI1539] - Pasqui, V. and Saint-Bauzel, L. and Sigaud, O. (2010). Characterization of a least effort user-centered trajectory for sit-to-stand assistance User-centered trajectory for sit-to-stand assistance.
Symposium on Dynamics modeling and interaction control in virtual and real environments IUTAM. Pages 197-204.
[ PDF | BIB ]
[2010ACTI1599] - Kozlova, O. and Sigaud, O. and Meyer, C. (2010). TeXDYNA: Hierarchical Reinforcement Learning in Factored MDPs.
From Animals to Animats: Proceedings of the 11th International Conference on Adaptive Behaviour (SAB 2010), Springer, publisher. Pages 489-500 .
[ PDF | BIB ]
[2010ACTN1538] - Marin, D. and Sigaud, O. (2010). Apprentissage par renforcement appliqué au contrôle moteur : reproduction du principe d'isochronie.
proceedings JFPDA. Pages 1-10. Besançon.
[ PDF | BIB ]
[2010COM1917] - Rigoux, L. and Sigaud, O. and Terekhov, A. and Guigon, E. (2010). Movement duration as an emergent property of reward directed motor control.
Proc Advances in Computational Motor Control, Symposium at the Society for Neuroscience Conference (Todorov E, Shadmehr R, Kording K, organizers). San Diego, CA, USA.
[ PDF | BIB ]
2009
[2009ACLN945] - Degris, T. and Sigaud, O. and Wuillemin, P.-H. (2009). Apprentissage par renforcement factorisé pour le comportement de personnages non joueurs .
Revue d'Intelligence Artificielle, Lavoisier, publisher. Vol 23 Pages 221-252.
[ PDF | BIB ]
[2009COS1013] - Sigaud , O. and Butz, M. V. and Kozlova, O. and Meyer, C. (2009). Anticipatory Learning Classifier Systems and Factored Reinforcement Learning.
LNAI 5499: Anticipatory Behavior in Adaptive Learning Systems: From Psychological Theories to Artificial Cognitive Systems, Springer, publisher. Pages 321-333.
[ PDF | BIB ]
[2009COS1468] - Salaun, C. and Padois, V. and Sigaud, O. (2009). A Two-Level Model of Anticipation-Based Motor Learning for Whole Body Motion.
Anticipatory Behavior in Adaptive Learning Systems, From Psychological Theories to Artificial Cognitive Systems, Springer, publisher. Vol 5499 Pages 229-246.
[ HTTP | DOI | BIB ]
[2009INVI2058] - Sigaud, O. (2009). A tutorial about Reinforcement Learning.
IAS-ISF Motor Days. Jerusalem. invited conference.
[ PDF | BIB ]
[2009INVN1853] - Pasqui, V. and Saint-Bauzel, L. and Sigaud, O. (2009). Une aide technique robotisée pour la mobilité des personnes âgées handicapées.
Congrès de la Société Française des Technologies pour l’Autonomie et de Gérontechnologie SFTAG. Université de Technologie de Troyes. invited conference.
[ BIB ]
[2009INVN2057] - Sigaud, O. (2009). Apprentissage en Robotique, pourquoi, comment ?.
Journées Nationales de la Recherche en Robotique. Sologne. invited conference.
[ PDF | BIB ]
[2009ACTI946] - Libeau, B. and Micaelli, A. and Sigaud, O. (2009). Transfer of Knowledge for a Climbing Virtual Human: A Reinforcement Learning Approach .
Proceedings IEEE International Conference on Robotics and Automation. Pages 2119-2124.
[ PDF | BIB ]
[2009ACTI997] - Kozlova, O. and Sigaud, O. and Meyer, C. (2009). Automated Discovery of Options in Factored Reinforcement Learning.
Proceedings of the ICML/UAI/COLT Workshop on Abstraction in Reinforcement Learning. Pages 24-29. Montreal, Canada.
[ PDF | BIB ]
[2009ACTI1020] - Kozlova, O. and Sigaud, O. and Wuillemin, P.-H. and Meyer, C. (2009). Considering Unseen States as Impossible in Factored Reinforcement Learning.
ECML PKDD 2009, Part I, LNAI 5781-0721 , Springer, publisher. Pages 721--735.
[ PDF | BIB ]
[2009ACTI1470] - Salaun, C. and Padois, V. and Sigaud, O. (2009). Control of redundant robots using learned models: an operational space control approach.
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems. Pages 878--885. Saint-Louis, USA.
[ HTTP | DOI | BIB ]
2008
[2008ACLI440] - Landau, S. and Sigaud, O. (2008). A Comparison between ATNoSFERES and LCSs on non-Markov problems.
Information Sciences. Vol 178 Pages 4482-4500.
[ PDF | BIB ]
[2008COS840] - Sigaud, O. and Garcia, F. (2008). Apprentissage par renforcement.
Processus décisionnels de Markov en intelligence artificielle (volume 1), Lavoisier, publisher. Ch 2 Pages 53--88.
[ PDF | BIB ]
[2008COS841] - Degris, T. and Sigaud, O. (2008). Représentations factorisées.
Processus décisionnels de Markov en intelligence artificielle (volume 2), Lavoisier, publisher. Ch 2 Pages 51--79.
[ PDF | BIB ]
[2008DO842] - Sigaud, O. and Buffet, O. (2008). Processus décisionnels de Markov en intelligence artificielle (volume 1).
, Lavoisier, publisher.
[ PDF | BIB ]
[2008DO843] - Buffet, O. and Sigaud, O. (2008). Processus décisionnels de Markov en intelligence artificielle (volume 2).
, Lavoisier, publisher.
[ PDF | BIB ]
[2008ACTI826] - Degris, T. and Sigaud, O. and Wuillemin, P.-H. (2008). Exploiting Additive Structure in Factored MDPs for Reinforcement Learning.
Proceedings EWRL, Springer, LNAI 5323, publisher. Pages 15-26. Lille, France.
[ PDF | BIB ]
[2008ACTI1601] - Manier, S. and Sigaud, O. (2008). Compacting a Rule Base into an and/or Diagram for Game AI.
GAMEON. Pages 77-85.
[ PDF | BIB ]
[2008ACTN827] - Kozlova, O. and Sigaud, O. and Meyer, C. (2008). Apprentissage par renforcement hiérarchique dans les MDP factorisés.
Actes JFPDA. Pages 93-102. Metz, France.
[ PDF | BIB ]
[2008ACTN918] - Rigoux, L. and Sigaud, O. (2008). Un modèle computationnel de l'automatisation motrice.
Proceedings of the second french conference on Computational Neuroscience. Pages 152-157. Marseille.
[ PDF | BIB ]
2007
[2007ACLI483] - Sigaud, O. and Wilson, S. W. (2007). Learning Classifier Systems: A Survey.
Journal of Soft Computing, Springer, publisher. Vol 11 No 11 Pages 1065-1078.
[ PDF | BIB ]
[2007ACLN474] - Sigaud, O. (2007). Les systèmes de classeurs : un état de l'art.
Revue d'Intelligence Artificielle, Hermès, publisher. Vol 21 Pages 75-106.
[ PDF | BIB ]
[2007COS739] - Butz, M.V. and Sigaud, O. and Pezzulo, G. and Baldassarre, G. (2007). Anticipations, Brains, Individual and Social Behavior: An Introduction to Anticipatory Systems .
Anticipatory Behavior in Adaptive Learning Systems : From Brains to Individual and Social Behavior , LNAI 4520, Springer, publisher. Pages 1-18. ISBN: 978-3-540-74261-6.
[ PDF | BIB ]
[2007DO738] - Butz, M.V. and Sigaud, O. and Pezzulo, G. and Baldassarre, G., editor(s) (2007). Anticipatory Behavior in Adaptive Learning Systems : From Brains to Individual and Social Behavior.
Anticipatory Behavior in Adaptive Learning Systems : From Brains to Individual and Social Behavior, LNAI 4520, Springer, publisher. ISBN: 978-3-540-74261-6.
[ BIB ]
[2007ACTI776] - Gabalda, B. and Rigoux, L. and Sigaud, O. (2007). Learning postures through sensorimotor training: a human simulation case study.
Proceedings of the Seventh International Conference on Epigenetic Robotics. Pages 29-36. Rutgers, Piscataway, NJ.
[ PDF | BIB ]
[2007ACTN782] - Degris, T. and Sigaud, O. and Wuillemin, P.-H. (2007). Apprentissage par renforcement exploitant la structure additive des MDP factorisés.
Actes de la conférence JFPDA'07. Pages 49-60. Grenoble.
[ PDF | BIB ]
[2007COM1436] - Durlin, R. and Salaun, C. and Sigaud, O. (2007). Apprentissage de la verticalisation sur un humain virtuel.
Journées Nationales de la Robotique Humanoïde. Montpellier, France.
[ PDF | BIB ]
2006
[2006ACLN383] - Flacher, F. and Sigaud, O. (2006). GACS : une approche ascendante pour la coordination spatiale.
Revue d'Intelligence Artificielle, Hermès, publisher. Vol 20 No 1 Pages 7--29.
[ PDF | BIB ]
[2006DO344] - Charpillet, F. and Garcia, F. and Perny, P. and Sigaud, O. (2006). Décision et planification dans l'incertain.
, Hermès, publisher.
[ BIB ]
[2006ACTI348] - Degris, T. and Sigaud, O. and Wuillemin, P.-H. (2006). Chi-square Tests Driven Method for Learning the Structure of Factored MDPs.
Proceedings of the 22nd Conference on Uncertainty in Artificial Intelligence (UAI), AUAI Press, publisher. Pages 122--129. Massachusetts Institute of Technology Cambridge, MA, USA.
[ PDF | BIB ]
[2006ACTI349] - Degris, T. and Sigaud, O. and Wuillemin, P.-H. (2006). Learning the Structure of Factored Markov Decision Processes in Reinforcement Learning Problems.
Proceedings of the 23rd International Conference on Machine Learning (ICML), ACM, publisher. Pages 257--264. Pittsburgh, Pennsylvania.
[ PDF | BIB ]
[2006ACTN350] - Degris, T. and Sigaud, O. and Wuillemin, P.-H. (2006). Apprentissage de la structure des processus de décision markoviens factorisés pour l'apprentissage par renforcement.
Actes de la conférence JFPDA'06. Pages 89-96. Toulouse.
[ PDF | BIB ]
2005
[2005ACLI414] - Gérard, P. and Meyer, J.-A. and Sigaud, O. (2005). Combining Latent Learning and Dynamic Programming in MACS.
European Journal of Operational Research, Elsevier, publisher. Vol 160 Pages 614--637.
[ PDF | BIB ]
[2005ACTI382] - Flacher, F. and Sigaud, O. (2005). GACS, an Evolutionary Approach to the Spatial Coordination of Agents.
Proceedings AAMAS 2005, ACM Press, publisher. Pages 1109-1110. Utrecht, The netherlands.
[ PDF | BIB ]
[2005ACTI391] - Gourdin, T. and Sigaud, O. (2005). Towards a Reinforcement Learning Module for Navigation in Video Games.
Proceedings of the ECML05 Workshop on Reinforcement Learning in Non-Stationary Environments. Pages 1-12. Porto, Portugal.
[ PDF | BIB ]
[2005ACTI441] - Landau,S. and Sigaud, O. and Schoenauer, M. (2005). ATNoSFERES revisited.
Proceedings of the Genetic and Evolutionary Computation Conference, GECCO-2005, ACM Press, publisher. Pages 1867-1874. Washington DC.
[ PDF | BIB ]
2004
[2004ACLI347] - Degris, T. and Sigaud, O. and Wiener, S. I. and Arleo, A. (2004). Rapid response of head direction cells to reorienting visual cues: A computational model.
Neurocomputing, Elsevier, publisher. Vol 58-60C Pages 675-682.
[ PDF | BIB ]
[2004ACLN482] - Sigaud, O. and Gérard, P. (2004). Apprentissage par renforcement indirect dans les systèmes de classeurs.
JEDAI. Vol 1 Pages 1-12.
[ PDF | HTTP | BIB ]
[2004ACTI381] - Flacher, F. and Sigaud, O. (2004). BASC, a Bottom-up Approach to automated design of Spatial Coordination.
From Animals to Animats 8: Proceedings of the Eighth International Conference on Simulation of Adaptive Behavior, MIT Press, publisher. Pages 435-444. Cambridge, MA.
[ PDF | BIB ]
[2004ACTI396] - Guessoum, Z. and Rejeb, L. and Sigaud, O. (2004). Using XCS to build Adaptive Agents.
Proceedings of the Fourth Symposium on Adaptive Agents and Multi-Agent Systems (AAMAS-4), AISB convention. Pages 101--106. Leeds.
[ PDF | BIB ]
[2004ACTI434] - Labbé, V. and Sigaud, O. (2004). Anticipation of Periodic Movements in Real Time 3D Environments.
Proceedings of the Anticipatory Behavior in Adaptive Learning Systems (ABiALS) 2004 Workshop. Pages 1-8. Los Angeles, CA.
[ PDF | HTTP | BIB ]
[2004ACTI439] - Landau, S. and Sigaud, O. (2004). A Michigan style architecture for learning finite state controllers: a first step.
Proceedings of the Seventh International Workshop on Learning Classifier Systems. Pages 1-8. Seattle, WA.
[ BIB ]
[2004ACTI476] - Sigaud, O. and Gourdin, T. and Wuillemin, P.-H. (2004). Improving MACS thanks to a comparison with 2TBNs.
Proceedings of the Genetic and Evolutionary Computation Conference, GECCO'04, Springer, publisher. Pages 810--823.
[ PDF | BIB ]
[2004THDR473] - Sigaud, O. (2004). Comportements adaptatifs pour des agents dans des environnements informatiques complexes.
. Paris. These. Université Pierre et Marie Curie, Paris 6.
[ PDF | BIB ]
2003
[2003ACLN380] - Flacher, F. and Sigaud, O. (2003). Coordination spatiale émergente par champs de potentiel.
Technique et Science Informatique, Hermès, publisher. Vol 22 No 2 Pages 171--195.
[ PDF | BIB ]
[2003COS342] - Butz, M. V. and Sigaud, O. and Gérard, P. (2003). Anticipatory Behavior: Exploiting Knowledge about the Future to Improve Current Behavior.
LNCS 2684 : Anticipatory Behavior in Adaptive Learning Systems, Springer-Verlag, publisher.
[ PDF | BIB ]
[2003COS343] - Butz, M. V. and Sigaud, O. and Gérard, P. (2003). Internal Models and Anticipations in Adaptive Learning Systems.
LNCS 2684 : Anticipatory Behavior in Adaptive Learning Systems, Springer-Verlag, publisher.
[ PDF | BIB ]
[2003COS438] - Landau, S. and Picault, S. and Sigaud, O. and Gérard, P. (2003). Further Comparison between ATNoSFERES and XCSM.
Learning Classifier Systems LNCS 2661, Springer-Verlag, publisher. Pages 99--117.
[ PS | BIB ]
[2003DO335] - Butz, M. V. and Sigaud, O. and Gérard, P., editor(s) (2003). LNCS 2684 : Anticipatory Behavior in Adaptive Learning Systems.
, Springer-Verlag, publisher.
[ BIB ]
[2003ACTI419] - Gérard, P. and Sigaud, O. (2003). Designing Efficient Exploration with MACS: Modules and Function Approximation.
Proceedings of the Genetic and Evolutionary Computation Conference 2003 (GECCO03), Springer-Verlag, publisher. Pages 1882--1893. Chicago, IL.
[ PDF | BIB ]
[2003ACTN481] - Sigaud, O. and Gérard, P. (2003). Apprentissage par renforcement indirect dans les systèmes de classeurs.
Actes des journées PDMIA. Pages 1-8. In french.
[ BIB ]
2002
[2002ACLI420] - Gérard, P. and Stolzmann, W. and Sigaud, O. (2002). YACS : Yet a new Learning Classifier System using Anticipation..
Journal of Soft Computing, Springer, publisher. Vol 6 No 3-4 Pages 216--228.
[ PDF | BIB ]
[2002COS475] - Sigaud, O. and Flacher, F. (2002). Vers une approche dynamique de la sélection de l'action.
Approche dynamique de la cognition artificielle, Hermès, publisher. Pages 163--178. Paris, France.
[ PDF | BIB ]
[2002ACTI379] - Flacher, F. and Sigaud, O. (2002). Spatial Coordination through Social Potential Fields and Genetic Algorithms.
From Animals to Animats 7. Proceedings of the Seventh International Conference on Simulation of Adaptive Behavior, MIT Press, publisher. Pages 389--390.
[ PDF | BIB ]
[2002ACTI436] - Landau, S. and Picault, S. and Sigaud, O. and Gérard, P. (2002). A Comparison between ATNoSFERES and XCSM.
Proceedings of the Genetic and Evolutionary Computation Conference, GECCO 2002, Morgan Kaufmann, publisher. Pages 926--933. New York, NY.
[ PDF | BIB ]
[2002ACTI437] - Landau, S. and Picault, S. and Sigaud, O. and Gérard, P. (2002). Further Comparison between ATNoSFERES and XCSM.
IWLCS-02. Proceedings of the Fourth International Workshop on Learning Classifier Systems, Springer, publisher. Pages 1-8.
[ PS | BIB ]
2001
[2001ACLN418] - Gérard, P. and Sigaud, O. (2001). Généralisation et apprentissage latent dans les systèmes de classeurs.
Extraction des Connaissances et Apprentissage, Hermès, publisher. Vol 1 No 3 Pages 87--114.
[ PDF | BIB ]
[2001COS479] - Sigaud, O. and Gérard, P. (2001). Using Classifier Systems as Adaptive Expert Systems for Control.
LNAI 1996 : Advances in Classifier Systems, Springer-Verlag, publisher. Pages 138--157.
[ PDF | BIB ]
[2001COS480] - Sigaud, O. and Gérard, P. (2001). Being Reactive by Exchanging Roles: an Empirical Study.
LNAI 2103 : Balancing reactivity and Social Deliberation in Multiagent Systems, Springer-Verlag, publisher. Pages 138--157.
[ PDF | BIB ]
[2001ACTI416] - Gérard, P. and Sigaud, O. (2001). Adding a Generalization Mechanism to YACS.
Proceedings of the Genetic and Evolutionary Computation Conference 2001 (GECCO01), Morgan Kaufmann, publisher. Pages 951--957. San Francisco, CA.
[ PDF | BIB ]
[2001ACTI417] - Gérard, P. and Sigaud, O. (2001). YACS : Combining Anticipation and Dynamic Programming in Classifier Systems.
LNAI 1996 : Advances in Classifier Systems, Springer, publisher. Pages 52--69.
[ PDF | BIB ]
2000
[2000ACTI415] - Gérard, P. and Sigaud, O. (2000). Combining Anticipation and Dynamic Programming in Classifier Systems.
Proceedings of the Third International Workshop on Learning Classifier Systems. Pages 1-8.
[ PDF | BIB ]
[2000ACTI478] - Sigaud, O. and Gérard, P. (2000). The use of roles in a multiagent adaptive simulation.
Proceedings of the 14th European Conference in Artificial Intellligence, Workshop on Balancing reactivity and Social Deliberation in Multiagent Systems. Pages 150-172. Berlin, Germany.
[ PDF | BIB ]
1999
[1999ACTN477] - Sigaud, O. and Gérard, P. (1999). Contribution au problème de la sélection de l'action en environnement partiellement observable.
Intelligence Artificielle Située, Hermès, publisher. Pages 129--146. Paris, France.
[ PDF | BIB ]