The optimal decision making under uncertainty research group in A&O/TAO elaborates on the expertise gained with the world level computer-Go player MoGo, aimed at advances in reinforcement learning and noisy optimization. The motivating applications lie in the domains of energy management and games.


Groups
  Learning and Optimization

Joint Inria project teams


Research highlights


Contracts & grants


Software & patents


Collaborations


Members
  DUPIN Nicolas

Ph.D. dissertations & Faculty habilitations

° Algorithm control and hyper-parameter tuning
° Algorithms for networked systems
° Automated Proof, SMT and Applications
° Automated Reasoning
° Combinatorics
° Compilation and code optimization
° Data-Centric Languages and Systems
° Deductive Verification of Programs
° Digital Fabrication
° Distributed algorithms
° Distributed Design
° Engineering of interactive systems
° Fab lab
° Formal Model-Based Testing
° Formalisation and Proof of Numerical Programs
° Formalisation of (Specification and Programming) Languages in Proof Assistants
° Generative design methods
° Graph Theory
° Green networks
° Heterogeneous Wireless Networks
° High-performance computing
° Human-Computer Interaction
° Integration of Data and Knowledge
° Interaction and visualization paradigms
° Large scale modelling