Home - Pierre-Yves Oudeyer

I am research director (DR1) at Inria, heading the Flowers team at Inria Bordeaux Sud-Ouest (see PhD students). I was previously a permanent researcher in Sony Computer Science Laboratory for 8 years (1999-2007).

I have been studying lifelong autonomous learning, and the self-organization of behavioural, cognitive and cultural structures, at the frontiers of artificial intelligence, machine learning, cognitive sciences and educational technologies.

In particular, I study mechanisms of exploration in autonomous learning, with a special focus on mechanisms enabling agents to set their own goals, and how this can self-organize curriculum learning. This includes mechanisms of intrinsically motivated learning (also called curiosity-driven active learning), autonomous unsupervised exploration, imitation and social learning, multimodal statistical inference, embodiment and maturation and self-organization.

This developmental machine learning work was recently integrated with deep reinforcement learning techniques, where unsupervised deep learning techniques are used to learn spaces in which to self-generate goals, and where curiosity-driven exploration is used to discover independently controllable features and solve efficiently sparse reward problems in Deep RL.

I consider cognitive development as a complex dynamical system which needs to be understood through systemic thinking, leveraging tools and concepts from computational sciences (artificial intelligence, machine learning and robotics), neuroscience and psychology. I consider algorithmic models as powerful scientific languages to express theories of cognitive development in the living.

I am also working on applications of this research in three fields: adaptive human-computer interfaces, educational technologies and open-source robotics for art and education.

In practice, this has led me to follow two mutually reinforcing research activities (yet with two different epistemological perspectives):

Cognitive science: understanding human cognitive development, where computers and robots are used as conceptual and experimental tools in constant dialog with developmental psychology, neuroscience and linguistics (see an overview in these slides).
Artificial intelligence: constructing machines and robots, inspired by mechanisms of the living, which are capable of lifelong development and adaptation to the physical and social world, including mechanisms of autonomous unsupervised exploration and learning (see an overview in these slides).

Quick links:

Science: Publications, Videos, Talks, Patents, Google Scholar
Bio: Bio, Awards, Collective Responsibilities,
Team: Flowers team, PhD students, Jobs
Team activity report: Quadriennal Flowers lab report (2013-2016)
Projects: Models of curiosity in humans, Active learning and curiosity in robots, Poppy Project, Perceptual multimodal learning, Human-robot interaction, e-learning technologies, Emotional Speech synthesis and recognition, Models of speech and language acquisition and evolution
Popular science: Articles, museum exhibits and interviews, press, Art/Science projects, videos in english, vidéos en français
Join open science discussion on the Flowers open lab forum

Selected publications:

Selected publications by topic:

Cognitive Science: Models of Human Development and Language Evolution

Overview (Curiosity-driven Developmental Process and the Evolution of Language)
- Oudeyer, P-Y. and Smith. L. (2016) How Evolution may work through Curiosity-driven Developmental Process , Topics in Cognitive Science, 1-11.
- Oudeyer, P-Y. (2018) Computational Theories of Curiosity-driven Learning, in “The New Science of Curiosity”, ed. G. Gordon, NOVA.

Models of Curiosity and its Role in Self-Organization of Developmental Structures
- Oudeyer P-Y, Kaplan , F. and Hafner, V. (2007) Intrinsic Motivation Systems for Autonomous Mental Development IEEE Transactions on Evolutionary Computation, 11(2), pp. 265–286.
- Gottlieb, J., Oudeyer, P-Y., Lopes, M., Baranes, A. (2013) Information Seeking, Curiosity and Attention: Computational and Neural Mechanisms, Trends in Cognitive Science, , 17(11), pp. 585-596. Bibtex Pdf preprint
- Kaplan F. and Oudeyer P-Y. (2007a) In search of the neural circuits of intrinsic motivation, Frontiers in Neuroscience, 1(1), pp.225–236.
- SOFTWARE: A number of these models are available in the open-source Explauto Python library, available on GitHub (code written by C. Moulin-Frier and P. Rouanet): Explauto: an open-source Python library to study autonomous exploration in developmental robotics Clément Moulin-Frier; Pierre Rouanet; Pierre-Yves Oudeyer ICDL-Epirob – International Conference on Development and Learning, Epirob, Oct 2014, Genoa, Italy.
Curiosity in humans: behavioral experiments and data mining
- Adrien Baranes, Pierre-Yves Oudeyer, Jacqueline Gottlieb (2015) Eye Movements Reveal Epistemic Curiosity in Human Observers, Vision Research, 117, pp. 81-90. [pdf]
- Adrien Baranes, Pierre-Yves Oudeyer, Jacqueline Gottlieb (2014) The effects of task difficulty, novelty and the size of the search space on intrinsically motivated exploration, Frontiers in Neuroscience, 2014, 8 (317), pp.1-9. <10.3389/fnins.2014.00317> [pdf] [Bib]
Curiosity in Language Acquisition and Speech Development
- Forestier S, Oudeyer P-Y. (2017) A Unified Model of Speech and Tool Use Early Development. Proceedings of the 39th Annual Meeting of the Cognitive Science Society.
- Oudeyer, P-Y. (2015) Open challenges in understanding development and evolution of speech forms: The roles of embodied self-organization, motivation and active exploration , Journal of Phonetics, in press, http://dx.doi.org/10.1016/j.wocn.2015.09.001.
- Moulin-Frier, C., Nguyen, S.M., Oudeyer, P-Y. (2014) Self-organization of early vocal development in infants and machines: the role of intrinsic motivation, Frontiers in Psychology (Cognitive Science), 4(1006), Bibtex
- Kaplan, F., Oudeyer, P-Y., Bergen B. (2008) Computational Models in the Debate over Language Learnability, Infant and Child Development, 17(1), pp. 55–80.
- Oudeyer P-Y., Kaplan F. (2006) Discovering Communication, Connection Science, 18(2), pp. 189–206.
Language Acquisition, Sensorimotor Grounding and the Gavagai problem
- Mangin O, Filliat D, ten Bosch L, Oudeyer P-Y (2015) MCA-NMF: Multimodal Concept Acquisition with Non-Negative Matrix Factorization, PLoS ONE 10(10): e0140732. doi:10.1371/journal.pone.0140732
- Cederborg, T. and Oudeyer, P-Y. (2013) From Language to Motor Gavagai: Unified Imitation Learning of Multiple Linguistic and Non-linguistic Sensorimotor Skills, IEEE Transactions on Autonomous Mental Development. 5(3), pp. 222-239.
Self-Organization in the Evolution of Speech
- Oudeyer, P-Y. (2006) Self-Organization in the Evolution of Speech, Oxford University Press.
- Oudeyer, P-Y. (2005) The Self-Organization of Speech Sounds, Journal of Theoretical Biology, 233(3), pp. 435–449.
Darwinian Dynamics in Language Evolution
- Oudeyer P-Y., Kaplan F. (2007) Language Evolution as a Darwinian Process: Computational Studies, Cognitive Processing, , 8(1), pp. 21–35.
- Oudeyer, P-Y (2005) How phonological structures can be culturally selected for learnability, Adaptive Behavior, 13(4), pp. 269–280.

Machine Learning, Artificial Intelligence, Deep RL and Developmental Robotics,

Conceptual framework:
- Oudeyer, P-Y. (2018) Computational Theories of Curiosity-driven Learning, in “The New Science of Curiosity”, ed. G. Gordon, NOVA.
Curiosity-driven deep unsupervised learning
- Laversanne-Finot, A., Péré, A., Oudeyer, P-Y. (2018) Curiosity Driven Exploration of Learned Disentangled Goal Spaces, In Proceedings of Conference on Robot Learning (CoRL 2018).
Curiosity-driven Deep Reinforcement Learning
- Colas, C., Sigaud, O., Oudeyer, P. Y. (2018). GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms. In Proceedings of International Conference on Machine Learning (ICML 2018), arXiv preprint arXiv:1802.05054. Other links: code and blog post.
- Péré, A., Forestier, S., Sigaud, O., & Oudeyer, P. Y. (2018). Unsupervised Learning of Goal Spaces for Intrinsically Motivated Goal Exploration. In Proceedings of International Conference on Learning Representations (ICLR 2018), arXiv preprint arXiv:1803.00781. Other links: code.
Intrinsically Motivated Goal Exploration and Curriculum Learning
- Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learning.
  Forestier S, Oudeyer P-Y. (2017)
  arXiv:1708.02190
- Baranes, A., Oudeyer, P-Y. (2013) Active Learning of Inverse Models with Intrinsically Motivated Goal Exploration in Robots, Robotics and Autonomous Systems, 61(1), pp. 49-73.
Intrinsically Motivated Goal Exploration and Strategic Learning
- Nguyen, M., & Oudeyer, P.-Y. (2013). Active choice of teachers, learning strategies and goals for a socially guided intrinsic motivation learner. Paladyn: Journal of Behavioural Robotics, 3(3), 136–146.
- Lopes M., Oudeyer P-Y. (2012) The Strategic Student Approach for Life-Long Exploration and Learning, in Proceedings of IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-Epirob), San Diego, USA. https://flowers.inria.fr/mlopes/myrefs/12-ssp.pdf
Developmental Constraints for Lifelong Robot Learning in High-Dimensions
- Oudeyer P-Y., Baranes A., Kaplan F. (2013) Intrinsically Motivated Learning of Real-World Sensorimotor Skills with Developmental Constraints, in Intrinsically Motivated Learning in Natural and Artificial Systems, eds. Baldassarre G. and Mirolli M., Springer.
Knowledge-based Intrinsic Motivation and Artificial Curiosity in Developmental Robotics
- Oudeyer P-Y. and Kaplan F. (2007) Intrinsic Motivation Systems for Autonomous Mental Development Oudeyer P-Y, Kaplan , F. and Hafner, V. (2007) IEEE Transactions on Evolutionary Computation, 11(2), pp. 265–286.
- Oudeyer P-Y. and Kaplan F. (2007) What is intrinsic motivation? A typology of computational approaches , Frontiers in Neurorobotics, 1:6
- Kaplan, F., Oudeyer, P-Y (2003) Motivational principles for visual know-how development In Prince, C.G. et al., editors, Proceedings of the 3rd international workshop on Epigenetic Robotics : Modeling cognitive development in robotic systems, no. 101, pages 73-80, 2003. Lund University Cognitive Studies.
- SOFTWARE: A number of these models are available in the open-source Explauto Python library, available on GitHub (code written by C. Moulin-Frier and P. Rouanet): Explauto: an open-source Python library to study autonomous exploration in developmental robotics Clément Moulin-Frier; Pierre Rouanet; Pierre-Yves Oudeyer ICDL-Epirob – International Conference on Development and Learning, Epirob, Oct 2014, Genoa, Italy.
Intrinsically Motivated Exploration for Tool Use
- Forestier S, Oudeyer P-Y. 2016. Modular Active Curiosity-Driven Discovery of Tool Use. 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
Multimodal Learning of Language in Robots
- Cederborg, T. and Oudeyer, P-Y. (2013) From Language to Motor Gavagai: Unified Imitation Learning of Multiple Linguistic and Non-linguistic Sensorimotor Skills, IEEE Transactions on Autonomous Mental Development. 5(3), pp. 222-239.
- Mangin O, Filliat D, ten Bosch L, Oudeyer P-Y (2015) MCA-NMF: Multimodal Concept Acquisition with Non-Negative Matrix Factorization, PLoS ONE 10(10): e0140732. doi:10.1371/journal.pone.0140732
Human-Robot Interaction: Adaptive Interfaces
- Pierre Rouanet, Pierre-Yves Oudeyer, Fabien Danieau and David Filliat (2013) Teaching a robot how to recognize new visual objects: a study of the impact of interfaces IEEE Transactions on Robotics, vol.29, no.2, pp.525,541, Bibtex
- Grizou, J., Lopes, M. and Oudeyer, P-Y. (2013) Robot Learning Simultanously a Task and How to Interpret Human Instructions, Proceedings of IEEE International Conference on Development and Learning and Epigenetic Robotics, IEEE ICDL-Epirob, Osaka, Japan.
- Kaplan, F., Oudeyer, P-Y., Kubinyi, E. and Miklosi, A. (2002) Robotic clicker training, Robotics and Autonomous Systems, 38(3-4), pp. 197–206.
Emotional Speech Synthesis and Recognition
- Oudeyer P-Y. (2003) The production and recognition of emotions in speech: features and algorithms International Journal in Human-Computer Studies, 59(1-2), pp. 157–183.

Adaptive Human-Machine Interfaces, BCI, Emotional Speech Processing

Calibration-Free Brain-Computer Interfaces (BCI)
- I. Iturrate, J. Grizou, J. Omedes, P.-Y. Oudeyer, M. Lopes and L. Montesan (2015) Exploiting task constraints for self-calibrated brain-machine interface control using error-related potentials, PLOS One, 2015.
- Jonathan Grizou; Iñaki Iturrate; Luis Montesano; Pierre-Yves Oudeyer; Manuel Lopes (2014) Calibration-Free BCI Based Control , Proceedings of Twenty-Eighth AAAI Conference on Artificial Intelligence, Jul 2014, Quebec, Canada. Bibtex
Adaptive Learning of how to Interpret Human Instruction/Social Signals
- Grizou, J., Lopes, M. and Oudeyer, P-Y. (2013) Robot Learning Simultanously a Task and How to Interpret Human Instructions, Proceedings of IEEE International Conference on Development and Learning and Epigenetic Robotics, IEEE ICDL-Epirob, Osaka, Japan. [videos of talk] Bibtex
- Thomas Cederborg; Pierre-Yves Oudeyer (2013) From Language to Motor Gavagai: Uniﬁed Imitation Learning of Multiple Linguistic and Non-linguistic Sensorimotor Skills, IEEE Transactions on Autonomous Mental Development (TAMD), IEEE, 2013 Bibtex
Emotional Speech Synthesis and Recognition
- Oudeyer P-Y. (2003) The production and recognition of emotions in speech: features and algorithms, International Journal in Human-Computer Studies, 59(1-2), pp. 157–183. Bibtex
Intuitive Interfaces for Human-Robot Interaction
- Pierre Rouanet; Pierre-Yves Oudeyer ; Fabien Danieau; David Filliat (2013) The Impact of Human-Robot Interfaces on the Learning of Visual Objects , IEEE Transactions on Robotics, IEEE Robotics and Automation Society, 2013, 29 (2), pp. 525-541 Bibtex
- Robotic clicker training Kaplan, F., Oudeyer, P-Y., Kubinyi, E. and Miklosi, A. (2002) Robotics and Autonomous Systems, 38(3-4), pp. 197–206. Bibtex

Educational Technologies

Developmental Active Learning for Personalization and Optimization in Online Educational Software
- Benjamin Clement, Didier Roy, Pierre-Yves Oudeyer, Manuel Lopes (2015) Multi-Armed Bandits for Intelligent Tutoring Systems , Journal of Educational Data Mining (JEDM), Vol 7, No 2, 2015.
Educational robotics
- Didier Roy, Gordana Gerber, Stéphane Magnenat, Fanny Riedo, Morgane Chevalier, Pierre-Yves Oudeyer, Francesco Mondada (2015) IniRobot: a pedagogical kit to initiate children to concepts of robotics and computer science , 6th International Conference on Robotics in Education, 2015.

Outreach Projects

Poppy: an Open-Source 3D Printed Robotic Platform

Link to information about the Poppy humanoid robot : Poppy Project web site. Poppy is an open-source 3D printed robot for science, education and art designed by the Flowers team. It was built to study the impact of the body on sensorimotor development and cognition: it makes it possible to really consider the body as an experimental variable. See article at Humanoids 2013 conference.

Poppy Overview from Poppy Project on Vimeo.

IniRobot: un kit pédagogique pour l'initiation à la robotique à l'école primaire

IniRobot: IniRobot est une série d’activités pédagogiques “clés en main” destinée à la découverte de la robotique et de la programmation à l’école primaire, en particulier lors des activités périscolaires. Ce kit est libre d’utilisation (Creative Commons CC-BY-SA) et utilise le robot Thymio développé à l’EPFL. Il est déployé en France dans les activités périscolaires des écoles de plusieurs villes, dont Lille, Talence et Lormont. Il a été développé par Didier Roy, Thomas Guitard et Pierre-Yves Oudeyer dans l’équipe Flowers, et est partagé sur le site participatif Dessine-moi un robot.

Art and Science

I collaborate regularly with artist within project that explore the frontiers between art and science. This has been the opportunity to create original connections between the general public and our scientific projects, in particular by bringing people to ask themselves and to ourselves stimulating questions about the position of such scientific projects within society at large.

Examples of such projects include:

Artistic residency “Etres et Numériques” (2014), a study of movement and emotions through the interaction between the humanoid robot Poppy and a dancer. This happened at Lycée Saintonge, in Bordeaux, and also included workshop with young students allowing them to discover various aspects of robotics and its role in society.#01- artistique | robotique | médiation – Recherche chien noir à tête d’ours, résidence Lycée Saintonge. Bordeaux 2014. from comacina, capsule créative on Vimeo.
Ergo-Robots Experiment at “Mathematics: A Beautiful Elsewhere” (2012) Exhbition at Fondation Cartier pour l’Art Contemporain (Paris, France), with a collaboration with movie maker David Lynch.
C2M1 (2010): “associate scientist” with artists for an art live theatrical performance about the impact of technology upon language (with C2M1 group in Boulogne-Billancourt, lead by Magali Desbazeille and Siegfried Canto). Video complète du spectacle C2M ici.

News

New papers on curiosity, deep RL and lifelong learning

Laversanne-Finot, A., Péré, A., Oudeyer, P-Y. (2018) Curiosity Driven Exploration of Learned Disentangled Goal Spaces, In Proceedings of Conference on Robot Learning (CoRL 2018).

Oudeyer, P-Y. (2018) Computational Theories of Curiosity-driven Learning, in “The New Science of Curiosity”, ed. G. Gordon, NOVA.

Colas, C., Sigaud, O., Oudeyer, P. Y. (2018). GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms. In Proceedings of International Conference on Machine Learning (ICML 2018), arXiv preprint arXiv:1802.05054. Other links: code and blog post.

Péré, A., Forestier, S., Sigaud, O., & Oudeyer, P. Y. (2018). Unsupervised Learning of Goal Spaces for Intrinsically Motivated Goal Exploration. In Proceedings of International Conference on Learning Representations (ICLR 2018), arXiv preprint arXiv:1803.00781. Other links: code.

Gibson Lecture at Cornell University (04/17)

I gave the 29th Gibson Lecture at University of Cornell, Ithaca. The talk was about “Active exploration mechanisms in autonomous learning and development” (slides), and in particular I presented several robotic and machine learning models of automatic intrinsically motivated curriculum learning.

NIPS 2016 Demo awards: Flowers team demo was runner up

The demonstration “Intrinsically motivated multitask reinforcement learning” built by the Flowers team was runner up of the NIPS 16 demo competition. This demonstration shows real time online acquisition of repertoires of high-dimensional nested skills (including tool use) with curiosity-drive goal exploration processes.

Human Frontier Science Program grant Curiosity accepted (March 2016)

Together with J. Gottlieb, M. Lopes, and C. Kidd, we have been awarded a 3 year grant by the HFSP program for an interdisciplinary research program to study active exploration and learning, and their computational modeling, in infants and monkeys. We are looking for motivated PhD and postdoc candidates to work on this project.

Second Interdisciplinary Symposium on Information Seeking, Curiosity and Attention, Sept. 2016

Together with J. Gottlieb and T. Gliga, we have co-organized the Second Interdisciplinary Symposium on Information Seeking, Curiosity and Attention in London, in september 2016. This great event has gathered researchers from neuroscience, psychology and computer science/machine learning: J. Nelson, D. Markant, R. Ligneul, S. Kouider, M. Gruber, K. Murayama, J. O’Reilly, G. Baldassarre, P. Dayan, P-Y. Oudeyer, K. Doya, W. Shultz, A. Bell, L. Hunt, J. Gottlieb, D. Bell, K. Begus, L. Goupil, L. Feigenson, D. Bavelier, T. Gliga. Most videos and slides of the symposium are available on the Neurocuriosity 2016 symposium web site.

Poppy Project: Open-Source 3D printed Robotics Creation platform for Science, Education and Art

Poppy project is an open-source platform for the creation, use and sharing of interactive 3D printed robots. It was initially developed by the Flowers team at Inria, and is now supported by a large community of contributors and users. The new website of Poppy Project is out, and provides all links to hardware, software and documentation resources to build and/or obtain an open-source 3D printed Poppy robot, under the Creative Commons licence (CC-BY-SA). Poppy Humanoid was the first worldwide open-source 3D printed full body humanoid robot. Poppy Torso and Poppy Ergo are other robots that can be built and modified with the Poppy platform. The Poppy platform is used widely for projects in open science, open education from primary schools to university, and art. Join the interdisciplinary community on the forum, and explore the GitHub repositories.