Main
Dr. Remy Chaput
Ph.D. in Computer Science (Artificial Intelligence)
Publications
Multi-objective reinforcement learning: an ethical perspective
International Workshop MODeM, ECAI'24Timon Deschamps, Rémy Chaput, Laëtitia Matignon. Multi-objective reinforcement learning: an ethical perspective. Multi-Objective Decision Making Workshop, ECAI, Oct 2024, Santiago de Compostela, Spain. HAL : hal-04711682
Multi-objective reinforcement learning: an ethical perspective
National Conference RJCIA'24Timon Deschamps, Rémy Chaput, Laetitia Matignon. Multi-objective reinforcement learning: an ethical perspective. RJCIA, Jul 2024, La Rochelle, France. HAL : hal-04711663
Adaptive reinforcement learning of multi-agent ethically-aligned behaviours: the QSOM and QDSOM algorithms
Technical Report ArXivRémy Chaput, Olivier Boissier, Mathieu Guillermin. Adaptive reinforcement learning of multi-agent ethically-aligned behaviours: the QSOM and QDSOM algorithms. 2023. HAL : hal-04379426
Learning to identify and settle dilemmas through contextual user preferences
International Conference ICTAI'23Rémy Chaput, Laëtitia Matignon, Mathieu Guillermin. Learning to identify and settle dilemmas through contextual user preferences. IEEE International Conference on Tools with Artificial Intelligence (ICTAI), Nov 2023, Atlanta, United States. DOI : 10.1109/ICTAI59109.2023.00075. HAL : hal-04349804.
Ethical Smart Grid: a Gym environment for learning ethical behaviours
Journal Article JOSSClément Scheirlinck, Rémy Chaput, Salima Hassas. Ethical Smart Grid: a Gym environment for learning ethical behaviours. Journal of Open Source Software, 2023, 8 (88), pp.5410. DOI : 10.21105/joss.05410. HAL : hal-04187666.
Apprentissage de comportements éthiques multi-valeurs par combinaison d’agents juges symboliques et d’agents apprenants
Journal Article ROIARémy Chaput, Jérémy Duval, Olivier Boissier, Mathieu Guillermin, Salima Hassas. Apprentissage de comportements éthiques multi-valeurs par combinaison d’agents juges symboliques et d’agents apprenants. Revue Ouverte d'Intelligence Artificielle, 2023, 4 (2), pp.41-66. DOI : 10.5802/roia.56. HAL : hal-04161020.
AJAR: An Argumentation-based Judging Agents Framework for Ethical Reinforcement Learning
International Conference AAMAS'23Benoît Alcaraz, Olivier Boissier, Rémy Chaput, Christopher Leturc. AJAR: An Argumentation-based Judging Agents Framework for Ethical Reinforcement Learning. AAMAS '23: International Conference on Autonomous Agents and Multiagent Systems, International Foundation for Autonomous Agents and Multiagent Systems, May 2023, London, United Kingdom. DOI : 10.5555/3545946.3598956. HAL : hal-04127943.
Artificial Moral Advisors: enhancing human ethical decision-making
International Conference ETHICS'23Marco Tassella, Rémy Chaput, Mathieu Guillermin. Artificial Moral Advisors: enhancing human ethical decision-making. 2023 IEEE International Symposium on Ethics in Engineering, Science, and Technology (ETHICS), IEEE, May 2023, West Lafayette, United States. pp.1-5, DOI : 10.1109/ETHICS57328.2023.10155026. HAL : hal-04127849.
A Multi-Agent Approach to Combine Reasoning and Learning for an Ethical Behavior
International Conference AIES'21Rémy Chaput, Jérémy Duval, Olivier Boissier, Mathieu Guillermin & Salima Hassas (2021). « A Multi-Agent Approach to Combine Reasoning and Learning for an Ethical Behavior ». AIES '21: AAAI/ACM Conference on AI, Ethics, and Society, 21 mai 2021, Virtual Event USA (États-Unis), pp. 13-23. doi : 10.1145/3461702.3462515. HAL : emse-03318195.
Approche multi-agent combinant raisonnement et apprentissage pour un comportement éthique
National Conference JFSMA'21Rémy Chaput, Jérémy Duval, Olivier Boissier, Mathieu Guillermin & Salima Hassas (2021). « Approche multi-agent combinant raisonnement et apprentissage pour un comportement éthique ». Journées Francophones sur les Systèmes Multi-Agents, 30 juin 2021, Bordeaux (France). HAL : emse-03278353.
Explanation for Humans, for Machines, for Human-Machine Interactions?
Workshop Explainable Agency in AI, AAAI'21Rémy Chaput, Amélie Cordier, Alain Mille. Explanation for Humans, for Machines, for Human-Machine Interactions?. AAAI-2021, Explainable Agency in Artificial Intelligence WS, AAAI, Feb 2021, Virtual Conference, United States. HAL : hal-03106286.
Une perspective historique sur l'IA explicable
Technical ReportAlain Mille, Rémy Chaput, Amélie Cordier. Une perspective historique sur l'IA explicable Document préparatoire à un tutorial AFIA juillet 2020. [Rapport de recherche] LIRIS UMR 5205 CNRS/INSA de Lyon/Université Claude Bernard Lyon 1/Université Lumière Lyon 2/École Centrale de Lyon. 2020. HAL : hal-03352469
Apprentissage adaptatif de comportements éthiques
National Conference JFSMA'20Rémy Chaput, Olivier Boissier, Mathieu Guillermin, Salima Hassas. Apprentissage adaptatif de comportements éthiques. 28e Journées Francophones sur les Systèmes Multi-Agents (JFSMA'2020), Jun 2020, Angers, France. HAL : hal-03012127.
Teaching
AI and Deep Learning
CPE Lyon- Lectures (CM, 8h) + Practical works (TP, 12h)
- Co-responsible for this module
- Level 3rd year of engineering cycle (Bac+5)
- Introduction to AI, Machine Learning, well-known algorithms and techniques
Ethics of engineer
Mines Saint-Étienne- Visiting Lecturer (CM, 3h)
- A 3-hour course I gave to engineers about the ethics of AI
- Level 1st year of engineering cycle
- Introduction to AI, societal impact of AI, discussion about ethical issues
Intelligent Agents
University Claude Bernard Lyon 1- Teaching Assistant (practical works - TP, 9h) in 2023
- Level Master 2, specialty Artificial Intelligence
Bases of Artificial Intelligence
University Claude Bernard Lyon 1- Teaching Assistant (practical works - TP since 2019, 52h; tutorials - TD since 2020, 15h)
- Level Master 1
- Problem modelling; Constraint solving
Algorithmic and Object-Oriented Programming
University Claude Bernard Lyon 1- Teaching Assistant (practical works - TP, 76h ; tutorials - TD, 42h)
- Organized projects, wrote examination papers
- Level Bachelor 3
- UML, Object-Oriented Programming, Java language
Bio-inspired Intelligence
University Claude Bernard Lyon 1- Teaching Assistant (practical works and projects - TP, 6h)
- Supervised projects on genetic algorithms
- Level Master 2
- Python language
Article peer-review
IROS'24
Peer-reviewed 1 article for the IROS'2024 conferenceDomains: Reinforcement Learning, Robotics, Multi-Agent Systems
ECAI'23
Peer-reviewed 2 articles for the ECAI'2023 conferenceDomains: Reinforcement Learning, Large Language Models
AAMAS'23
Peer-reviewed 1 article for the AAMAS'2023 conference as a sub-reviewerDomains: AI, Multi-Agent Systems
EXTRAAMAS
Peer-reviewed 2 articles for the EXTRAAMAS'23 workshopDomain: AI and Explainability
Digital Society
Peer-reviewed 1 article for a special edition of the Digital Society journalMachine Ethics, AI and Society
EXTRAAMAS
Peer-reviewed 2 articles for the EXTRAAMAS'22 workshopDomain: AI and Explainability
Research Projects
ACCELER-AI
Project funded by Agence Nationale de la Recherche (ANR-22-CE23-0028)- Multidisciplinary and multi-university consortium.
- Communication of the project to national and international seminaries.
- Mentoring 1x Master intern and 1x Ph.D student.
Ethics.AI
Regional project, funded by Pack Ambition Recherche (Auvergne-Rhône-Alpes)- Multidisciplinary and multi-university consortium.
- Participation in and organization of meetings.
- Drafting minutes, writing reports.
- (Co-)Supervision of interns: 5x Master 2nd year, 1x Master 1st year.
Professional Experience
Associate Professor
CPE Lyon Lyon, FranceTeacher at the CPE engineering school. Responsibilities include:
- Organizing courses, handling external teachers.
- Preparing courses’ syllabus.
- Preparing and supervising lectures, practical works (mainly in 4Y and 5Y courses).
- Research on AI and Ethics-related subjects.
Post-doctorate researcher
LIRIS Lyon, FranceMember of the ACCELER-AI ANR project. Responsibilities include:
- Reviewing state of the art in Multi-Agent and Multi-Objective Reinforcement Learning.
- Publishing scientific articles; communicating in conferences.
- Designing and running experiments.
- Mentoring a Ph.D. student.
- Teaching at Bachelor and Master level.
Research engineer
LIRIS Lyon, FranceResearch engineer in the Ethics.AI project. Responsibilities include:
- Implementation of an open-source simulator of ethical Smart Grid.
- Publishing scientific articles; participating to seminaries.
- Reporting on the project’s results; developing a website.
Ph.D. student
LIRIS Lyon, FrancePh.D. student in the Ethics.AI project. Responsibilities include:
- Organizing project meetings; preparing the agenda, taking the minutes.
- Reviewing the state of the art on Machine Ethics; positioning our approach.
- Developing the use-case and implementation of our approach.
- Publishing scientific articles; communicating in conferences and seminaries.
- Mentoring 5x research interns (Master 2) and 1x project (Master 1).
- Teaching courses at the University, at Bachelor and Master level.
Research internship
LIRIS Lyon, FranceResearch internship in a lab. Responsibilities include:
- Reviewing state of the art; proposing solutions.
- Implementing proof-of-concepts learning algorithms.
Research project
LIRIS Lyon, France6-months research project as part of the curriculum (Master’s orientation project - POM). Title: Multi-label categorization for large web-based raw biography texts, under the supervision of Dr. Frédéric Armetta and Dr. Marc Bertin. Responsibilities include:
- Improving an existing algorithm for multi-label classification of documents.
- Running experiments to validate the algorithm performances, and compare to baselines.
- Reviewing the SOTA and writing a scientific article.
Education
Doctorate in Computer Science
Université Claude Bernard Lyon 1, LIRIS Lyon, FranceThesis subject: Learning behaviours aligned with moral values in a multi-agent system: guiding reinforcement learning with symbolic judgments
Jury members:
- Parisa Ghodous (President)
- Grégory Bonnet (Reviewer)
- Marija Slavkovik (Reviewer)
- Alain Dutech (Examiner)
- Juan A. Rodríguez-Aguilar (Examiner)
- Salima Hassas (Supervisor)
- Olivier Boissier (Co-supervisor)
- Mathieu Guillermin (Co-supervisor)