Dynamic Programming And Social Learning Via Replicator Dynamics
This paper introduces a social learning algorithm for recursive decision problems faced by players in large anonymous games. The algorithm keeps track of only the distributions of agents over possible state-action pairs. State update, value update and behavior update constitute the three stages of the algorithm. The stability of the algorithm is studied. Numerical applications to consumption problems with and without cash-in-advance constraints are considered.
To our knowledge, this item is not available for
download. To find whether it is available, there are three
1. Check below under "Related research" whether another version of this item is available online.
2. Check on the provider's web page whether it is in fact available.
3. Perform a search for a similarly titled item that would be available.
|Date of creation:||05 Jul 2000|
|Date of revision:|
|Contact details of provider:|| Postal: CEF 2000, Departament d'Economia i Empresa, Universitat Pompeu Fabra, Ramon Trias Fargas, 25,27, 08005, Barcelona, Spain|
Fax: +34 93 542 17 46
Web page: http://enginy.upf.es/SCE/
More information through EDIRC
When requesting a correction, please mention this item's handle: RePEc:sce:scecf0:190. 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: (Christopher F. Baum)
If references are entirely missing, you can add them using this form.