Learning Nash equilibria with bandit feedback

Maryam Kamgarpour IAM Seminar
November 23, 2020 3:00 pm
Decision-making in multi-agent systems arises in engineering
applications ranging from electricity markets to communication and transportation networks. I discuss decision-making of multiple players with coupled objectives. In this setting, a Nash equilibrium is a stable solution concept, since no agent finds it profitable to unilaterally deviate from her choice. Due to geographic distance, privacy concerns, or simply the scale of these systems, each player can only base her decision on local information. I present our algorithm on learning Nash equilibria in convex games and discuss its convergence.


RSVP here.