ISE


The framework of multi-agent game-theoretic learning explores how individual agent strategies evolve in response to the strategies of others. A central question is whether these evolving strategies converge to classical solution concepts, such as Nash equilibrium.
This talk adopts a control-theoretic perspective by recognizing that learning agents interacting with one another form a feedback system. Learning dynamics are modeled as open dynamical systems that map payoffs, regardless of their source, into strategy updates, while the game itself provides the feedback interconnection.
The focus is on uncoupled learning, where agents update strategies based solely on observed payoffs, without explicit knowledge of utility functions (their own or of others). This perspective enables the use of control-theoretic tools to both analyze and synthesize learning dynamics.
We first exploit that convergence to Nash equilibrium corresponds to feedback stability. The main part of the talk establishes that uncoupled learning can, in general, lead to mixed-strategy Nash equilibrium, while highlighting that the required learning dynamics are not universal and may sometimes involve seemingly irrational behavior. We go on to show how a control-theoretic perspective supports compositional analysis of learning in games using game-theoretic extensions of passivity theory.