Skip to content. Skip to navigation
CIM Menus

A Contract-Based Model for Directed Network Formation

Prof. Shie Mannor < >
Centre for Intelligent Machines McGill University

June 23, 2005 at  10:00 AM
Zames Seminar Room - MC437

We are concerned with learning to act optimally in a dynamic, noisy, and competitive environment. Our model deviates from classical game theory as we assume that the other agents in the environment may act irrationally and arbitrarily. We look for strategies that take advantage of possible deviations of the other agents from an adversarial behavior.

We present two solution concepts for such environments. The first concept is based on the empirical measurement of statistics related to the non-stationary elements in the environment. We take a worst-case estimate over unknown information and re-define the problem as a vector-valued stochastic game. We define a concrete goal, the convex Bayes envelope, and show that it is attainable. This envelope is shown to be safe (above the worst-case performance guarantees) and adaptive (strictly above the worst-case performance guarantees if the non-stationary elements appear non-hostile). The second concept is based on viewing the stochastic game as a repeated super-game with imperfect monitoring. We show that this approach leads to different performance guarantees which are also safe and adaptive.