### Abstract

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 update the estimated value function rapidly enough, then each agent learns the true value function associated with the optimal action with probability 1 and almost always takes the optimal action asymptotically. Journal of Economic Literature Classification Number: C62, D83.

Original language | English |
---|---|

Pages (from-to) | 78-114 |

Number of pages | 37 |

Journal | Journal of Economic Theory |

Volume | 101 |

Issue number | 1 |

DOIs | |

State | Published - 2001 Jan 1 |

### Fingerprint

### Keywords

- Discontinuous decision rule
- Rational expectations
- Recursive learning
- Search
- Stochastic approximation

### Cite this

}

*Journal of Economic Theory*, vol. 101, no. 1, pp. 78-114. https://doi.org/10.1006/jeth.2001.2791

**Convergence of least squares learning in self-referential discontinuous stochastic models.** / Cho, In Koo.

Research output: Contribution to journal › Article

TY - JOUR

T1 - Convergence of least squares learning in self-referential discontinuous stochastic models

AU - Cho, In Koo

PY - 2001/1/1

Y1 - 2001/1/1

N2 - 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 update the estimated value function rapidly enough, then each agent learns the true value function associated with the optimal action with probability 1 and almost always takes the optimal action asymptotically. Journal of Economic Literature Classification Number: C62, D83.

AB - 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 update the estimated value function rapidly enough, then each agent learns the true value function associated with the optimal action with probability 1 and almost always takes the optimal action asymptotically. Journal of Economic Literature Classification Number: C62, D83.

KW - Discontinuous decision rule

KW - Rational expectations

KW - Recursive learning

KW - Search

KW - Stochastic approximation

UR - http://www.scopus.com/inward/record.url?scp=0035207235&partnerID=8YFLogxK

U2 - 10.1006/jeth.2001.2791

DO - 10.1006/jeth.2001.2791

M3 - Article

AN - SCOPUS:0035207235

VL - 101

SP - 78

EP - 114

JO - Journal of Economic Theory

JF - Journal of Economic Theory

SN - 0022-0531

IS - 1

ER -