Awards



  • 2nd Place of the AFIA (French Association of Artificial Intelligence) prize for the best thesis in Artificial Intelligence

Phd Thesis



  • My Phd Thesis (in French) untitled "Apprentissage Hors-Ligne avec Démonstrations Expertes" defended the 14th of November 2014. My Thesis

Publications



  • International journals

    1. Bilal Piot, Matthieu Geist and Olivier Pietquin. Bridging the Gap between Imitation Learning and Inverse Reinforcement Learning. In the IEEE Transactions on Neural Networks and Learning Systems. 2016 (status : accepted).Paper&Slides


  • Arxiv papers

    1. Bilal Piot, Matthieu Geist and Olivier Pietquin. Difference of Convex Functions Programming Applied to Control with Expert Data. Arxiv 2016.Paper
    2. Matthieu Geist, Bilal Piot and Olivier Pietquin. Should one minimize the expected Bellman residual or maximize the mean value? Arxiv 2016.Paper
    3. Julien Pérolat, Florian Strub, Bilal Piot and Olivier Pietquin. Learning Nash Equilibrium for General-Sum Markov Games from Batch Data. Arxiv 2016.Paper


  • National journals

    1. Edouard Klein, Bilal Piot, Matthieu Geist and Olivier Pietquin. Classification structurée pour l'apprentissage par renforcement inverse. Revue d'Intelligence Artificielle, 27(2/2013): 155-170, Mai 2013.


  • Book chapters

    1. Maurizio Mancini, Laurent Ach, Emeline Bantegnie, Tobias Baur, Nadia Berthouze, Bilal Piot and others. Laugh When You're Winning. Innovative and Creative Developments in Multimodal Interaction Systems, 2014. Springer.


  • International Conferences

    1. 2017


    2. Julien Pérolat, Florian Strub, Bilal Piot and Olivier Pietquin. Learning Nash Equilibrium for General-Sum Markov Games from Batch Data. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS 2017), 2017.


    3. 2016


    4. Julien Pérolat, Bilal Piot, Matthieu Geist, Bruno Scherrer and Olivier Pietquin. Softened Approximate Policy Iteration for Markov Games. In Proceedings of the Thirty third International Conference of Machine Learning (ICML 2016), 2016. Paper
    5. Layla El Asri, Bilal Piot, Matthieu Geist, Romain Laroche and Olivier Pietquin. Score-based Inverse Reinforcement Learning. In Proceedngs of the 15th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2016), 2016. Paper & Poster
    6. Julien Pérolat, Bilal Piot, Bruno Scherrer and Olivier Pietquin. On the Use of Non-Stationary Strategies for Solving Two-Player Zero-Sum Markov Games. In Proceedings of the 19th International Conference on Artificial Intelligence and Statistics (AISTATS 2016), 2016.Paper & Supplementary & Poster


    7. 2015


    8. Julien Pérolat, Bilal Piot, Bruno Scherrer and Olivier Pietquin. Approximate Dynamic Programming for Two-Player Zero-Sum Markov Games. In Proceedings of the Thirty Second International Conference of Machine Learning (ICML 2015), 2015. Paper
    9. Thibault Munzer, Bilal Piot, Matthieu Geist, Olivier Pietquin and Manuel Lopes. Inverse Reinforcement Learning in Relational Domains. In International Joint Conferences on Artificial Intelligence (IJCAI 2015), 2015. Paper
    10. Bilal Piot, Matthieu Geist and Olivier Pietquin. Imitation Learning Applied to Embodied Conversational Agents. In Machine Learning and Interactive Systems (MLIS 2015), 2015. Paper


    11. 2014


    12. Bilal Piot, Matthieu Geist and Olivier Pietquin. Difference of Convex Functions Programming for Reinforcement Learning. In Advances in Neural Information Processing Systems (NIPS 2014), 2014. NIPS spotlight.Paper & Poster & Supplementary
    13. Bilal Piot, Matthieu Geist and Olivier Pietquin. Predicting when to laugh with structured classification. In Annual Conference of the International Speech Communication Association (InterSpeech 2014), 2014.Paper & Poster
    14. Bilal Piot, Matthieu Geist and Olivier Pietquin. Boosted Bellman Residual Minimization Handling Expert Demonstrations. In European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD 2014), 2014.Paper & Poster
    15. Bilal Piot, Matthieu Geist and Olivier Pietquin. Boosted and Reward-regularized Classification for Apprenticeship Learning. In Proceeding of the thirteenth International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2014), 2014.Paper & Poster


    16. 2013


    17. Bilal Piot, Matthieu Geist and Olivier Pietquin. Learning from demonstrations : Is it worth estimating a reward function ? In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD 2013), 2013.Paper & Poster
    18. Radoslaw Niewiadomski, Jennifer Hofmann, Jérome Urbain, Tracey Platt, Johannes Wagner, Bilal Piot and others. Laughaware virtual agent and its impact on user amusement. In Proceedings of the Twelfth International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2013), 2013.Paper
    19. Edouard Klein, Bilal Piot, Matthieu Geist and Olivier Pietquin. A cascaded supervised learning approach to inverse reinforcement learning. In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD 2013), 2013.Paper


    20. 2012


    21. Edouard Klein, Matthieu Geist, Bilal Piot and Olivier Pietquin. Inverse reinforcement learning through structured classification. In Advances in Neural Information Processing Systems (NIPS 2012), 2012.Paper


  • National Conferences

    1. Edouard Klein, Bilal Piot, Matthieu Geist et Olivier Pietquin. Classification structurée pour l'apprentissage par renforcement inverse. Dans les actes de la Conférence Francophone sur l'Apprentissage Automatique (Cap 2012), Nancy, France, 2012.


  • International and National Conferences without proceeedings

    1. 2016


    2. Bilal Piot, Matthieu Geist and Olivier Pietquin. Batch Policy Iteration for Continuous Domains. Presented (20 minutes oral presentation) in the 13th European Workshop of Reinforcement Learning (EWRL 2016), Barcelona (Spain), 2016.
    3. Julien Pérolat, Bilal Piot, and Olivier Pietquin. A Study of Value Iteration with Non-Stationary Strategies in General Sum Markov Games. Presented (20 minutes oral presentation) in the NIPS workshop Learning, Inference and Control of Multi-Agent Systems (MALIC 2016), Barcelona (Spain), 2016.


    4. 2014


    5. Bilal Piot, Matthieu Geist et Olivier Pietquin. Méthode de minimisation du résidu de Bellman boostée qui tient compte des démonstrations expertes. Dans Journées Francophone de Plannification, Décision et Apprentissage (JFPDA 2014), 2014.


    6. 2013


    7. Bilal Piot, Matthieu Geist et Olivier Pietquin. Classification régularisée par la récompense pour l'Apprentissage par Imitation". In Journées Francophones de Plannification, Décision et Apprentissage (JFPDA), Lille (FRANCE), 2013.
    8. Matthieu Geist, Edouard Klein, Bilal Piot, Yan Guermeur and Olivier Pietquin. Around Inverse Reinforcement Learning and Score-based Classification. In 1st Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2013), Princeton, USA, 2013.
    9. Bilal Piot, Matthieu Geist and Olivier Pietquin. Learning from demonstrations: Is it worth estimating a reward function?. In 1st Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2013), Princeton, USA, 2013.
    10. Edouard Klein, Bilal Piot, Matthieu Geist et Olivier Pietquin. Apprentissage par renforcement inverse en cascadant classification et régression. Dans Journées Francophones de Plannification, Décision et Apprentissage (JFPDA 2013), 2013.
    11. Bilal Piot, Matthieu Geist et Olivier Pietquin. Apprentissage par démonstrations : vaut-il la peine d'estimer une fonction de récompense?. In Journées Francophones de Plannification, Décision et Apprentissage (JFPDA), 2013.


    12. 2012


    13. Edouard Klein, Bilal Piot, Matthieu Geist et Olivier Pietquin. Structured Classification for Inverse Reinforcement Learning. In European Workshop on Reinforcement Learning (EWRL 2012), Edinburgh, UK, 2012.