Plans of Action
No 5859, Working Paper from Department of Economics, University of Pittsburgh
We introduce a decision theoretic foundation for a class of learning models in which thedecision maker's beliefs over the present uncertainty is dictated by the outcomes of herpast actions. This type of learning underlies models of strategic experimentation. Weconstruct a framework in which an alternative is a recursive function contingent at anystage on the outcomes of previous actions, and provide axiomatizations for subjectivediscounted expected utility maximization, both for independent actions and correlatedactions. We point out that models of strategic experimentation have inherent limitedobservability, which in turn leads to partial identification of the subjective belief structure. We show that a class of processes we refer to as strongly exchangeable are the fullcharacterization of Bayesianism in such environments.
New Economics Papers: this item is included in nep-mic and nep-upt
References: View references in EconPapers View complete reference list from CitEc
Citations View citations in EconPapers (1) Track citations by RSS feed
Downloads: (external link)
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
Persistent link: https://EconPapers.repec.org/RePEc:pit:wpaper:5859
Access Statistics for this paper
More papers in Working Paper from Department of Economics, University of Pittsburgh Contact information at EDIRC.
Bibliographic data for series maintained by Department of Economics, University of Pittsburgh ().