Monday, 15:15 - 15:40 h, Room: MA 041


Hao Jiang
Learning parameters and equilibria in noise-corrupted Cournot games with misspecified price functions

Coauthors: Sean Meyn, Uday Shanbhag


We consider an oligopolistic setting in which myopic firms compete in a repeated Nash-Cournot game. In accordance with the Cournot assumption, prices are set based on aggregate output levels. We develop distributed learning schemes in a regime where firms are ignorant of a complete specification of an affine price function; specifically, firms learn the equilibrium strategy and correct the misspecification in the price function by simultaneously incorporating noise-corrupted observations and demand function. Differentiated by informational assumptions, two sets of schemes are developed and their performance is demonstrated on a networked Nash-Cournot game:
(1) Learning under common knowledge with unobservable aggregate output: Here, payoff
functions and strategy sets are public knowledge (a common knowledge assumption) but aggregate output is unobservable. When firms may observe noise-corrupted prices, distributed best response schemes are developed which allow for simultaneously learning the equilibrium strategy and the misspecified parameter in an almost-sure sense. Furthermore, these statements may be extended to accommodate nonlinear generalizations of the demand function.


Talk 1 of the invited session Mon.3.MA 041
"Analysis and learning in variational inequalities" [...]
Cluster 3
"Complementarity & variational inequalities" [...]


  Payday Loans In Tennessee. Therefore, we can say that the active substances in its composition are more perfectly mixed. Vardenafil is not only present in the original Levitra, but also as part of its analogs.