Convergence of Least Squares Learning in Self-Referential Discontinuous Stochastic Models

We examine the stability of rational expectations equilibria in the class of models in which the decision of the individual agent is discontinuous with respect to the state variables. Instead of rational expectations, each agent learns the unknown parameters through a recursive stochastic algorithm. If the agents the estimated value function ``rapidly'' enough, then each agent learns the true value function associated with the optimal action with probability, and almost always takes the optimal action asymptotically. Accepted on for publication in: Paper is available at URL: In-Koo Cho University of Illinois [email protected] Department of Economics, 1206 S. 6th Street Champaign, 61820, USA 217-333-4579(Phone) 217-244-6678(Fax) Citation: In-Koo Cho, (2001) ''Convergence of Least Squares Learning in Self-Referential Discontinuous Stochastic Models'', Economics Bulletin, Vol. 28 no.9 p.A1. Submitted: April 27, 2001 Published: April 27, 2001. URL: http://www.accessecon.com/pubs/EB/2001/Volume28/EB-01AA0012A.pdf