
-
Olivier Sigaud
- Full Professor
- Team: Amac
- Office: 56-66 301
- Email: olivier.sigaud@sorbonne-universite.fr
- Phone:01.44.27.88.53
- Addresse: ISIR, Campus Pierre et Marie Curie, 4 place Jussieu, BC173, 75005 Paris
- Bio: Born in 1968. Engineer, Phd in Computer Science from Paris XI University (Orsay) in 1996, PhD in Philosophy from Paris I University in 2004. Employed at Dassault Aviation (aerospace company, St-Cloud) from 1995 to 2001. Then Assistant Professor and finally Professor at LIP6 then ISIR. Main research topics: reinforcement learning, learning for robotics, computational neurosciences of decision making in animals.
Publications
- Vaynee Sungeelee, Antoine Loriette, Olivier Sigaud, Baptiste Caramiaux. Co-Apprentissage Humain-Machine: Cas d'Étude en Acquisition de Compétences Motrices. 34ème conférence Francophone sur l'Interaction Humain-Machine, Apr 2023, Troyes, France. ⟨hal-03992717⟩
- Vaynee Sungeelee, Antoine Loriette, Olivier Sigaud, Baptiste Caramiaux. Co-Apprentissage Humain-Machine : Cas d’Étude en Acquisition de Compétences Motrices. 2023. ⟨hal-04014981⟩
- Thomas Carta, Clément Romac, Thomas Wolf, Sylvain Lamprier, Olivier Sigaud, et al.. Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning. Proceedings of Machine Learning Research, 202 (3676-3713), 2023. ⟨hal-03970122v3⟩
- Thomas Carta, Sylvain Lamprier, Pierre-Yves Oudeyer, Olivier Sigaud. EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RL. NeurIPS 2022 - Thirty-sixth Conference on Neural Information Processing Systems, Nov 2022, Nouvelle-Orléans, United States. ⟨hal-03902423⟩
- Hugo Caselles-Dupré, Olivier Sigaud, Mohamed Chetouani. Pragmatically Learning from Pedagogical Demonstrations in Multi-Goal Environments. Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022), Nov 2022, New Orleans, United States. ⟨hal-03828002⟩
- Alexandre Chenu, Nicolas Perrin-Gilbert, Olivier Sigaud. Divide & Conquer Imitation Learning. 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2022), Oct 2022, Kyoto, Japan. ⟨hal-03753530⟩
- Aloïs Pourchot, Kevin Bailly, Alexis Ducarouge, Olivier Sigaud. Neural Architecture Search for Fracture Classification. 29th IEEE International Conference on Image Processing (ICIP 2022), Oct 2022, Bordeaux, France. ⟨hal-03753702⟩
- Ahmed Akakzia, Olivier Sigaud. LEARNING OBJECT-CENTERED AUTOTELIC BEHAVIORS WITH GRAPH NEURAL NETWORKS. Conference on Lifelong Learning Agents - CoLLAs 2022, Aug 2022, Montréal, Canada. ⟨hal-03753526⟩
- Aloïs Pourchot, Kévin Bailly, Alexis Ducarouge, Olivier Sigaud. An extensive appraisal of weight-sharing on the NAS-Bench-101 benchmark. Neurocomputing, 2022, 498, pp.28-42. ⟨10.1016/j.neucom.2022.04.108⟩. ⟨hal-03706214⟩
-
Thomas Pierrot, Valentin Macé, Felix Chalumeau, Arthur Flajolet, Geoffrey Cideron, et al.. Diversity policy gradient for sample efficient quality-diversity optimization. GECCO '22: Genetic and Evolutionary Computation Conference, Jul 2022, Boston, United States. pp.1075-1083, ⟨10.1145/3512290.3528845⟩. ⟨hal-03864262⟩
[ HTTP ]
- Cédric Colas, Tristan Karch, Olivier Sigaud, Pierre-Yves Oudeyer. Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: A Short Survey. Journal of Artificial Intelligence Research, 2022, 74, ⟨10.1613/jair.1.13554⟩. ⟨hal-03901771⟩
- Thomas Pierrot, Valentin Macé, Felix Chalumeau, Arthur Flajolet, Geoffrey Cideron, et al.. DIVERSITY POLICY GRADIENT FOR SAMPLE EFFI-CIENT QUALITY-DIVERSITY OPTIMIZATION. Workshop on Agent Learning in Open-Endedness (ALOE) at ICLR 2022, 2022, virtual, Vatican City. ⟨hal-03753541⟩
- Olivier Sigaud, Hugo Caselles-Dupré, Cédric Colas, Ahmed Akakzia, Pierre-Yves Oudeyer, et al.. Towards Teachable Autonomous Agents. 2021. ⟨hal-03364200⟩
-
Alexandre Chenu, Nicolas Perrin-Gilbert, Stéphane Doncieux, Olivier Sigaud. Selection-Expansion: A Unifying Framework for Motion-Planning and Diversity Search Algorithms. 30th International Conference on Artificial Neural Networks - ICANN 2021, Sep 2021, Bratislava, Slovakia. pp.568-579, ⟨10.1007/978-3-030-86380-7_46⟩. ⟨hal-03404366⟩
[ HTTP ]
-
Thomas Pierrot, Nicolas Perrin-Gilbert, Olivier Sigaud. First-Order and Second-Order Variants of the Gradient Descent in a Unified Framework. 30th International Conference on Artificial Neural Networks - ICANN 2021, Sep 2021, Bratislava, Slovakia. pp.197-208, ⟨10.1007/978-3-030-86340-1_16⟩. ⟨hal-03404369⟩
[ HTTP ]
- Ahmed Akakzia, Cédric Colas, Pierre-Yves Oudeyer, Mohamed Chetouani, Olivier Sigaud. Grounding Language to Autonomously-Acquired Skills via Goal Generation. ICLR 2021 - Ninth International Conference on Learning Representation, May 2021, Vienna / Virtual, Austria. ⟨hal-03121146⟩
-
Anis Najar, Olivier Sigaud, Mohamed Chetouani. Teaching a Robot with Unlabeled Instructions: The TICS Architecture. AAMAS 2021, May 2021, London (virtual), United Kingdom. ⟨hal-03224574⟩
[ HTTP ]
- Alexandre Chenu, Nicolas Perrin-Gilbert, Stephane Doncieux, Olivier Sigaud. Selection-Expansion: A Unifying Framework for Motion-Planning and Diversity Search Algorithms. 2021. ⟨hal-03196479⟩
- Cédric Colas, Ahmed Akakzia, Pierre-Yves Oudeyer, Mohamed Chetouani, Olivier Sigaud. Language-Conditioned Goal Generation: a New Approach to Language Grounding in RL. 2021. ⟨hal-03099887⟩
- Cédric Colas, Tristan Karch, Olivier Sigaud, Pierre-Yves Oudeyer. Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Survey. 2021. ⟨hal-03099891⟩
-
Pierre Fournier, Cédric Colas, Mohamed Chetouani, Olivier Sigaud. CLIC: Curriculum Learning and Imitation for object Control in non-rewarding environments. IEEE Transactions on Cognitive and Developmental Systems, 2021, 13 (2), pp.239-248. ⟨10.1109/TCDS.2019.2933371⟩. ⟨hal-02370859⟩
[ HTTP ]
-
Guillaume Matheron, Nicolas Perrin, Olivier Sigaud. PBCS: Efficient Exploration and Exploitation Using a Synergy Between Reinforcement Learning and Motion Planning. Artificial Neural Networks and Machine Learning – ICANN 2020, Sep 2020, Bratislava, Slovakia. pp.295-307, ⟨10.1007/978-3-030-61616-8_24⟩. ⟨hal-03080918⟩
[ HTTP ]
-
Guillaume Matheron, Nicolas Perrin, Olivier Sigaud. Understanding Failures of Deterministic Actor-Critic with Continuous Action Spaces and Sparse Rewards. Artificial Neural Networks and Machine Learning – ICANN 2020, Sep 2020, Bratislava, Slovakia. pp.308-320, ⟨10.1007/978-3-030-61616-8_25⟩. ⟨hal-03080925⟩
[ HTTP ]
- Ryan Lober, Olivier Sigaud, Vincent Padois. Task Feasibility Maximization using Model-Free Policy Search and Model-Based Whole-Body Control. Frontiers in Robotics and AI, 2020, 7, ⟨10.3389/frobt.2020.00061⟩. ⟨hal-01620370v3⟩
- Stephane Doncieux, Nicolas Bredeche, Léni Kenneth Le Goff, Benoît Girard, Alexandre Coninx, et al.. DREAM Architecture: a Developmental Approach to Open-Ended Learning in Robotics. 2020. ⟨hal-02562103⟩
- Anis Najar, Olivier Sigaud, Mohamed Chetouani. Interactively shaping robot behaviour with unlabeled human instructions. Autonomous Agents and Multi-Agent Systems, 2020, 34 (2), ⟨10.1007/s10458-020-09459-6⟩. ⟨hal-02996137⟩
- Marwen Belkaid, Elise Bousseyrol, Romain Durand-de Cuttoli, Malou Dongelmans, Etienne K Duranté, et al.. Mice adaptively generate choice variability in a deterministic task. Communications Biology, 2020, 3, pp.34. ⟨10.1038/s42003-020-0759-x⟩. ⟨hal-02485779⟩
- Felix Rutard, Olivier Sigaud, Mohamed Chetouani. 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, 2020, Napoli, Italy. ⟨hal-03124262⟩
-
Aloïs Pourchot, Nicolas Perrin, Olivier Sigaud. Importance mixing: Improving sample reuse in evolutionary policy search methods. 2019. ⟨hal-02397754⟩
[ HTTP ]
-
Thomas Pierrot, Nicolas Perrin, Olivier Sigaud. First-order and second-order variants of the gradient descent in a unified framework. 2019. ⟨hal-02397757⟩
[ HTTP ]
- Marwen Belkaid, Jérémie Naudé, Philippe Faure, Olivier Sigaud. Modélisation des stratégies de génération de choix variables chez la souris. Conférence Nationale en Intelligence Artificielle, Jul 2019, Toulouse, France. ⟨hal-02328815⟩
- Cédric Colas, Pierre Fournier, Olivier Sigaud, Mohamed Chetouani, Pierre-Yves Oudeyer. CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning. ICML 2019 - Thirty-sixth International Conference on Machine Learning, Jun 2019, Long Beach, United States. ⟨hal-01934921v2⟩
- Cédric Colas, Olivier Sigaud, Pierre-Yves Oudeyer. A Hitchhiker's Guide to Statistical Comparisons of Reinforcement Learning Algorithms. ICLR Worskhop on Reproducibility, May 2019, Nouvelle-Orléans, United States. ⟨hal-02369859⟩
- Olivier Sigaud, Freek Stulp. Policy search in continuous action domains: An overview. Neural Networks, 2019, 113, pp.28-40. ⟨10.1016/j.neunet.2019.01.011⟩. ⟨hal-02182466⟩
- Cédric Colas, Olivier Sigaud, Pierre-Yves Oudeyer. How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experiments. 2018. ⟨hal-01890154⟩
- Cédric Colas, Olivier Sigaud, Pierre-Yves Oudeyer. GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms. International Conference on Machine Learning (ICML), Jul 2018, Stockholm, Sweden. ⟨hal-01890151⟩
- Alexandre Péré, Sébastien Forestier, Olivier Sigaud, Pierre-Yves Oudeyer. Unsupervised Learning of Goal Spaces for Intrinsically Motivated Goal Exploration. ICLR2018 - 6th International Conference on Learning Representations, Apr 2018, Vancouver, Canada. ⟨hal-01891758⟩
-
Nicolas Lehir, Alban Laflaquière, Olivier Sigaud. Identification of invariant sensorimotor structures as a prerequisite for the discovery of objects. Frontiers in Robotics and AI, 2018, 5, pp.70. ⟨10.3389/frobt.2018.00070⟩. ⟨hal-03124279⟩
[ HTTP ]
- Stéphane Doncieux, David Filliat, Natalia Díaz-Rodríguez, Timothy Hospedales, Richard Duro, et al.. Open-Ended Learning: A Conceptual Framework Based on Representational Redescription. Frontiers in Neurorobotics, 2018, 12, pp.59. ⟨10.3389/fnbot.2018.00059⟩. ⟨hal-01889947⟩
- Pierre Fournier, Olivier Sigaud, Mohamed Chetouani. Combining artificial curiosity and tutor guidance for environment exploration. Workshop on Behavior Adaptation, Interaction and Learning for Assistive Robotics at IEEE RO-MAN 2017, Aug 2017, Lisbon, Portugal. ⟨hal-01581363⟩
- Alexis Ducarouge, Olivier Sigaud. 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), Jul 2017, Caen, France. ⟨hal-01576352⟩
-
Cédric Colas, Olivier Sigaud, Pierre-Yves Oudeyer. 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), Jul 2017, Nancy, France. ⟨hal-01840576⟩
[ HTTP ]
- Chenyang Zhao, Timothy Hospedales, Freek Stulp, Olivier Sigaud. Tensor based knowledge transfer across skill categories for robot control. International Joint Conference in Artificial Intelligence (IJCAI), 2017, Melbourne, Australia. pp.1-7, ⟨10.24963/ijcai.2017/484⟩. ⟨hal-03124263⟩
- Luka Peternel, Olivier Sigaud, Jan Babič. Unifying Speed-Accuracy Trade-Off and Cost-Benefit Trade-Off in Human Reaching Movements. Frontiers in Human Neuroscience, 2017, 11, pp.615. ⟨10.3389/fnhum.2017.00615⟩. ⟨hal-01679624⟩
- Francesco Romano, Gabriele Nava, Morteza Azad, Jernej Camernik, Stefano Dafarra, et al.. The CoDyCo Project achievements and beyond: Towards Human Aware Whole-body Controllers for Physical Human Robot Interaction. IEEE Robotics and Automation Letters, 2017, ⟨10.1109/LRA.2017.2768126⟩. ⟨hal-01620789⟩
- Ryan Lober, Vincent Padois, Olivier Sigaud. Efficient Reinforcement Learning for Humanoid Whole-Body Control. IEEE-RAS International Conference on Humanoid Robots, Nov 2016, Cancun, Mexico. ⟨hal-01377831⟩
- Olivier Sigaud, Alain Droniou. Towards Deep Developmental Learning. IEEE Transactions on Cognitive and Developmental Systems, 2016, 8 (2), pp.99-114. ⟨10.1109/TAMD.2015.2496248⟩. ⟨hal-01331799⟩
- Olivier Sigaud, Clément Masson, David Filliat, Freek Stulp. Gated networks: an inventory. 2016. ⟨hal-01313601⟩
- Anis Najar, Olivier Sigaud, Mohamed Chetouani. Training a robot with evaluative feedback and unlabeled guidance signals. RO-MAN, 2016, New York, United States. pp.261-266, ⟨10.1109/ROMAN.2016.7745140⟩. ⟨hal-03124264⟩
-
Anis Najar, Olivier Sigaud, Mohamed Chetouani. Social-Task Learning for HRI. International Conference on Social Robotics, Oct 2015, Paris, France. pp.472-481, ⟨10.1007/978-3-319-25554-5_47⟩. ⟨hal-02422990⟩
[ HTTP ]