Grants
- PI of Inria-Japan associate team Real-life bandits (RELIANT), with Junya Honda, 2022-2024.
- Participant of associate team Data collection for Sustainable Crop management (DC4SCM) with Bihar Agriculture University, Inria, 2020-2022.
- co-PI of « RLRL: Real Life Reinforcement Learning » project, with Benoîte de Saporta (Université Montpellier, IMAG), 12 months.
- Participant of STIC-AmSud project EMISTRAL « Environmental Monitoring and Inspection Sailboat via Transfer, Reinforcement and Autonomous Learning », January 2021, 24 months, 47k€.
- co-PI of Chaire IA Apprentissage par renforcement (AppRenf) project (R-PILOTE-19-004-APPRENF), Fondation I-SITE ULNE within the project PILOTE from cluster HumAIn@Lille, with Philippe Preux, 400k€.
- Participant of I-Site Expand2 project B4H « Bandit for Health », 2019, 150k€
- PI of Action Exploratoire: Sequential Recommendation for Sustainable Gardening (SR4SG), September 2019, 48 months, 165k€
- PI of ANR JCJC: BAnDits Against non-Stationarity and Structure (BADASS), with Emilie Kaufmann and Richard Combes, November 2016, 42 months, 180k€.
- PI of GdT digicosmes : Sequential Structured Statistical Learning (SSSL), with Richard Combes and Kinda Khawam, September 2016, 12 months: 2k€.
- co-PI of IFCAM project: Contextual multi-armed bandits with hidden structure, with Aditya Gopalan. September 2016, 18 months: 7.5k€.
- PI of Inria Carnot : Forecasting in hydraulic networks, with Olivier Teytaud and Marc Schoenauer. October 2015, 12 months: 12 months engineer.
- co-PI of PEPS JCJC: Promo, with Rémi Bardenet. May 2015, 6 months: 7k€.
Dissemination
- 2019 RLSS – Reinforcement Learning Summer School
- 2018 ANR BADASS Lecture Series (Invited lecturer: Peter Grünwald) .
- 2018 EWRL workshop – European Workshop on Reinforcement Learning
- 2017 Workshop – Sequential Structured Statistical Learning
- 2014 NIPS Workshop – “From Bad Models to Good Policies” (Sequential Decision Making under Uncertainty)