Optimal Learning with Endogenous Data
This paper is concerned with the need for, and the implications of, $-optimality in learning problems. The authors consider a control problem in which a Bayesian decisionmaker faces a trade-off between expected current reward and accumulation of information. An example showing the need for the notion of $-optimality and the possibility of discontinuous transition functions is given. It is shown that there is always an $-optimal policy that allows the decisionmaker to learn any identified parameters, but that there are other $-optimal policies with very different limit behavior. Copyright 1989 by Economics Department of the University of Pennsylvania and the Osaka University Institute of Social and Economic Research Association.
Volume (Year): 30 (1989)
Issue (Month): 4 (November)
|Contact details of provider:|| Postal: 160 McNeil Building, 3718 Locust Walk, Philadelphia, PA 19104-6297|
Phone: (215) 898-8487
Fax: (215) 573-2057
Web page: http://www.econ.upenn.edu/ier
More information through EDIRC
|Order Information:|| Web: http://www.blackwellpublishing.com/subs.asp?ref=0020-6598 Email: |
When requesting a correction, please mention this item's handle: RePEc:ier:iecrev:v:30:y:1989:i:4:p:963-78. 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: (Wiley-Blackwell Digital Licensing)or ()
If references are entirely missing, you can add them using this form.