Research Repository

An Axiomatization of Learning Rules when Counterfactuals are not Observed

Mengel, Friederike and Rivas, Javier (2012) 'An Axiomatization of Learning Rules when Counterfactuals are not Observed.' The B.E. Journal of Theoretical Economics, 12 (1). pp. 1-19. ISSN 1935-1704

Full text not available from this repository.


In this paper we study learning procedures when counterfactuals (payoffs of not chosen actions) are not observed. The decision maker reasons in two steps: First, she updates her propensities for choosing each action after every payoff experience, where propensities can be interpreted as preferences. Then, she transforms these propensities into choice probabilities. We introduce a set of axioms on how propensities are updated and on how these propensities are translated into choices and study the decision marker's behavior when such axioms are in place. Our characterization includes the linear reinforcement learning rule from Roth and Erev (1995).

Item Type: Article
Uncontrolled Keywords: learning without counterfactuals; partial information; reinforcement learning
Subjects: H Social Sciences > HB Economic Theory
Divisions: Faculty of Social Sciences
Faculty of Social Sciences > Economics, Department of
SWORD Depositor: Elements
Depositing User: Elements
Date Deposited: 12 May 2013 16:36
Last Modified: 18 Aug 2022 12:36

Actions (login required)

View Item View Item