Stochastic approximation, Momentum, and Nash play
Main objects here are normal-form games, featuring uncertainty and noncooperative players who entertain local visions, form local approximations, and hesitate in making large, swift adjustments. For the purpose of reaching Nash equilibrium, or learning such play, we advocate and illustrate an algorithm that combines stochastic gradient projection with the heavyball method. What emerges is a coupled, constrained, second-order stochastic process. Some friction feeds into and stabilizes myopic approximations. Convergence to Nash play obtains under seemingly weak and natural conditions, an important one being that accumulated marginal payoffs remains bounded above.
|Date of creation:||03 Apr 2002|
|Date of revision:|
|Contact details of provider:|| Postal: |
Web page: http://www.uib.no/econ/
More information through EDIRC
When requesting a correction, please mention this item's handle: RePEc:uib:bereco:0209. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Bjørn Sandvik)
If references are entirely missing, you can add them using this form.