Home » Teams » Amac » Olivier Sigaud
  • Olivier Sigaud

  • Professeur des Universités
  • Équipe: Amac
  • Bureau: 56-66 301
  • Email: olivier.sigaud@sorbonne-universite.fr
  • Telephone:01.44.27.88.53
  • Addresse: ISIR, Campus Pierre et Marie Curie, 4 place Jussieu, BC173, 75005 Paris

Publications

  • Olivier Sigaud, Hugo Caselles-Dupré, Cédric Colas, Ahmed Akakzia, Pierre-Yves Oudeyer, Mohamed Chetouani (2021). Towards Teachable Autonomous Agents.
  • Alexandre Chenu, Nicolas Perrin-Gilbert, Stéphane Doncieux, Olivier Sigaud (2021). Selection-Expansion: A Unifying Framework for Motion-Planning and Diversity Search Algorithms. Artificial Neural Networks and Machine Learning – ICANN 2021 Vol 12894 Pages 568-579.
  • Thomas Pierrot, Nicolas Perrin-Gilbert, Olivier Sigaud (2021). First-Order and Second-Order Variants of the Gradient Descent in a Unified Framework. Artificial Neural Networks and Machine Learning – ICANN 2021 Vol 12892 Pages 197-208.
  • Ahmed Akakzia, Cédric Colas, Pierre-Yves Oudeyer, Mohamed Chetouani, Olivier Sigaud (2021). Grounding Language to Autonomously-Acquired Skills via Goal Generation. ICLR 2021 - Ninth International Conference on Learning Representation
  • Anis Najar, Olivier Sigaud, Mohamed Chetouani (2021). Teaching a Robot with Unlabeled Instructions: The TICS Architecture. AAMAS 2021
  • Alexandre Chenu, Nicolas Perrin-Gilbert, Stephane Doncieux, Olivier Sigaud (2021). Selection-Expansion: A Unifying Framework for Motion-Planning and Diversity Search Algorithms.
  • Cédric Colas, Tristan Karch, Olivier Sigaud, Pierre-Yves Oudeyer (2021). Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Survey.
  • Cédric Colas, Ahmed Akakzia, Pierre-Yves Oudeyer, Mohamed Chetouani, Olivier Sigaud (2021). Language-Conditioned Goal Generation: a New Approach to Language Grounding in RL.
  • Pierre Fournier, Cédric Colas, Mohamed Chetouani, Olivier Sigaud (2021). CLIC: Curriculum Learning and Imitation for object Control in non-rewarding environments. IEEE Transactions on Cognitive and Developmental Systems Vol 13 Pages 239-248.
  • Guillaume Matheron, Nicolas Perrin, Olivier Sigaud (2020). Understanding Failures of Deterministic Actor-Critic with Continuous Action Spaces and Sparse Rewards. Artificial Neural Networks and Machine Learning – ICANN 2020 Pages 308-320.
  • Guillaume Matheron, Nicolas Perrin, Olivier Sigaud (2020). PBCS: Efficient Exploration and Exploitation Using a Synergy Between Reinforcement Learning and Motion Planning. Artificial Neural Networks and Machine Learning – ICANN 2020 Pages 295-307.
  • Ryan Lober, Olivier Sigaud, Vincent Padois (2020). Task Feasibility Maximization using Model-Free Policy Search and Model-Based Whole-Body Control. Frontiers in Robotics and AI Vol 7
  • Stephane Doncieux, Nicolas Bredeche, Léni Le Goff, Benoît Girard, Alexandre Coninx, Olivier Sigaud, Mehdi Khamassi, Natalia Díaz-Rodríguez, David Filliat, Timothy Hospedales, Agoston Eiben, Richard Duro (2020). DREAM Architecture: a Developmental Approach to Open-Ended Learning in Robotics.
  • Anis Najar, Olivier Sigaud, Mohamed Chetouani (2020). Interactively shaping robot behaviour with unlabeled human instructions. Autonomous Agents and Multi-Agent Systems Vol 34
  • Marwen Belkaid, Elise Bousseyrol, Romain Durand-de Cuttoli, Malou Dongelmans, Etienne Duranté, Tarek Yahia, Steve Didienne, Bernadette Hanesse, Maxime Come, Alexandre Mourot, Jérémie Naudé, Philippe Faure, Olivier Sigaud (2020). Mice adaptively generate choice variability in a deterministic task. Communications Biology Vol 3 Pages 34.
  • Felix Rutard, Olivier Sigaud, Mohamed Chetouani (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
  • Aloïs Pourchot, Nicolas Perrin, Olivier Sigaud (2019). Importance mixing: Improving sample reuse in evolutionary policy search methods.
  • Thomas Pierrot, Nicolas Perrin, Olivier Sigaud (2019). First-order and second-order variants of the gradient descent in a unified framework.
  • Marwen Belkaid, Jérémie Naudé, Philippe Faure, Olivier Sigaud (2019). Modélisation des stratégies de génération de choix variables chez la souris. Conférence Nationale en Intelligence Artificielle
  • Cédric Colas, Pierre Fournier, Olivier Sigaud, Mohamed Chetouani, Pierre-Yves Oudeyer (2019). CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning. ICML 2019 - Thirty-sixth International Conference on Machine Learning
  • Cédric Colas, Olivier Sigaud, Pierre-Yves Oudeyer (2019). A Hitchhiker's Guide to Statistical Comparisons of Reinforcement Learning Algorithms. ICLR Worskhop on Reproducibility
  • Olivier Sigaud, Freek Stulp (2019). Policy search in continuous action domains: An overview. Neural Networks Vol 113 Pages 28-40.
  • Cédric Colas, Olivier Sigaud, Pierre-Yves Oudeyer (2018). How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experiments.
  • Cédric Colas, Olivier Sigaud, Pierre-Yves Oudeyer (2018). GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms. International Conference on Machine Learning (ICML)
  • Alexandre Péré, Sébastien Forestier, Olivier Sigaud, Pierre-Yves Oudeyer (2018). Unsupervised Learning of Goal Spaces for Intrinsically Motivated Goal Exploration. ICLR2018 - 6th International Conference on Learning Representations
  • Stéphane Doncieux, David Filliat, Natalia Díaz-Rodríguez, Timothy Hospedales, Richard Duro, Alexandre Coninx, Diederik M. Roijers, Benoît Girard, Nicolas Perrin, Olivier Sigaud (2018). Open-Ended Learning: A Conceptual Framework Based on Representational Redescription. Frontiers in Neurorobotics Vol 12 Pages 59.
  • Nicolas Lehir, Alban Laflaquière, Olivier Sigaud (2018). Identification of invariant sensorimotor structures as a prerequisite for the discovery of objects. Frontiers in Robotics and AI Vol 5 Pages 70.
  • Pierre Fournier, Olivier Sigaud, Mohamed Chetouani (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
  • Alexis Ducarouge, Olivier Sigaud (2017). The Successor Representation as a model of behavioural flexibility. Journées Francophones sur la Planification, la Décision et l'Apprentissage pour la conduite de systèmes (JFPDA 2017)
  • Cédric Colas, Olivier Sigaud, Pierre-Yves Oudeyer (2017). GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms. Journées Francophones sur la Planification, la Décision et l'Apprentissage pour la conduite de systèmes (JFPDA 2018)
  • Francesco Romano, Gabriele Nava, Morteza Azad, Jernej Camernik, Stefano Dafarra, Oriane Dermy, Claudia Latella, Maria Lazzaroni, Ryan Lober, Marta Lorenzini, Daniele Pucci, Olivier Sigaud, Silvio Traversaro, Jan Babič, Serena Ivaldi, Michael Mistry, Vincent Padois, Francesco Nori (2017). The CoDyCo Project achievements and beyond: Towards Human Aware Whole-body Controllers for Physical Human Robot Interaction. IEEE Robotics and Automation Letters
  • Chenyang Zhao, Timothy Hospedales, Freek Stulp, Olivier Sigaud (2017). Tensor based knowledge transfer across skill categories for robot control. International Joint Conference in Artificial Intelligence (IJCAI) Pages 1-7.
  • Luka Peternel, Olivier Sigaud, Jan Babič (2017). Unifying Speed-Accuracy Trade-Off and Cost-Benefit Trade-Off in Human Reaching Movements. Frontiers in Human Neuroscience Vol 11 Pages 615.
  • Ryan Lober, Vincent Padois, Olivier Sigaud (2016). Efficient Reinforcement Learning for Humanoid Whole-Body Control. IEEE-RAS International Conference on Humanoid Robots
  • Olivier Sigaud, Alain Droniou (2016). Towards Deep Developmental Learning. IEEE Transactions on Cognitive and Developmental Systems Vol 8 Pages 99-114.
  • Olivier Sigaud, Clément Masson, David Filliat, Freek Stulp (2016). Gated networks: an inventory.
  • Anis Najar, Olivier Sigaud, Mohamed Chetouani (2016). Training a robot with evaluative feedback and unlabeled guidance signals. RO-MAN Pages 261-266.
  • Anis Najar, Olivier Sigaud, Mohamed Chetouani (2015). Social-Task Learning for HRI. International Conference on Social Robotics Pages 472-481.
  • Alain Droniou, Serena Ivaldi, Olivier Sigaud (2015). Deep unsupervised network for multimodal perception, representation and classification. Robotics and Autonomous Systems Vol 71 Pages 83-98.
  • Ryan Lober, Vincent Padois, Olivier Sigaud (2015). Variance Modulated Task Prioritization in Whole-Body Control.
  • Anis Najar, Olivier Sigaud, Mohamed Chetouani (2015). Socially Guided XCS. GECCO Companion '15 Proceedings of the Companion Publication of the 2015 Annual Conference on Genetic and Evolutionary Computation Pages 1021-1028.
  • Florian Lesaint, Olivier Sigaud, Jeremy Clark, Shelly Flagel, Mehdi Khamassi (2015). Experimental predictions drawn from a computational model of sign-trackers and goal-trackers. Journal of Physiology - Paris Vol 109 Pages 78–86.
  • Freek Stulp, Olivier Sigaud (2015). Many regression algorithms, one unified model — A review. Neural Networks Vol 69 Pages 60-79.
  • Anis Najar, Olivier Sigaud, Mohamed Chetouani (2015). Socially guided xcs: using teaching signals to boost learning. GECCO (Companion) Pages 1021-1028.
  • Ryan Lober, Vincent Padois, Olivier Sigaud (2014). Multiple Task Optimization using Dynamical Movement Primitives for Whole-Body Reactive Control. IEEE-RAS International Conference on Humanoid Robots
  • Florian Lesaint, Olivier Sigaud, Mehdi Khamassi (2014). Accounting for Negative Automaintenance in Pigeons: A Dual Learning Systems Approach and Factored Representations. PLoS ONE
  • Thibaut Munzer, Freek Stulp, Olivier Sigaud (2014). Non-linear regression algorithms for motor skill acquisition: a comparison. 9èmes Journées Francophones de Planification, Décision et Apprentissage
  • Florian Lesaint, Olivier Sigaud, Shelly Flagel, Terry Robinson, Mehdi Khamassi (2014). Modelling Individual Differences in the Form of Pavlovian Conditioned Approach Responses: A Dual Learning Systems Approach with Factored Representation. PLoS Computational Biology Vol 10 Pages e1003466.
  • Isabelle Bloch, Régis Clouard, Marinette Revenu, Olivier Sigaud (2014). Intelligence artificielle et reconnaissance des formes, vision, apprentissage pour la robotique. L'Intelligence Artificielle : Frontières et Applications, Volume 3, série : Panorama de l'Intelligence Artificielle Pages 30 pp.
  • Alain Droniou, Serena Ivaldi, Olivier Sigaud (2014). Learning a Repertoire of Actions with Deep Neural Networks. Proceedings of ICDL-EpiRob Pages 6 p..