ANR PRC Delicio

Data and Prior, Machine Learning and Contro

Recent progress in machine learning (ML) is often attributed to methodological advances, as well as massive amounts of training data and compute. We propose to extend these advances to sequential decision-making of multiple agents for planning and control. Our focus is on learning realistic behaviors that require long-term planning and robust, stable control in the short term. Methodologically, this project is at cross roads of machine learning and control theory. These two disciplines have a long and rich history of interactions between them and their overlap is becoming more and more evident. The project proposes fundamental contributions: adding stability to the algorithms of reinforcement learning; data driven methods for robust control; hybrid ML / CT methods for multi-horizon control and planning; decentralized control. The methodological contributions of this fundamental IA project will be applied to the robust control of UAV fleets.

• Dates
  Paru le 12 mai 2023, Mis à jour le 9 novembre 2023