eduzhai > Applied Sciences > Engineering >

Learning generalized Nash equilibria in multi-agent dynamical systems via extremum seeking control

  • king
  • (0) Download
  • 20210505
  • Save

... pages left unread,continue reading

Document pages: 15 pages

Abstract: In this paper, we consider the problem of learning a generalized Nashequilibrium (GNE) in strongly monotone games. First, we propose a novelcontinuous-time solution algorithm that uses regular projections andfirst-order information. As second main contribution, we design a data-drivenvariant of the former algorithm where each agent estimates their individualpseudo-gradient via zero-order information, namely, measurements of theirindividual cost function values, as typical of extremum seeking control. Third,we generalize our setup and results for multi-agent systems with nonlineardynamics. Finally, we apply our algorithms to connectivity control in roboticsensor networks and distributed wind farm optimization.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×