Recency, consistent learning, and Nash equilibrium

FUDENBERG, Drew; LEVINE, David K.

doi:10.1073/pnas.1400987111

2014

Proceedings of the National Academy of Sciences of the United States of America, 2014, Vol. 111, No. 3 Supp., pp. 10826-10829

Cite

FUDENBERG, Drew, LEVINE, David K., Recency, consistent learning, and Nash equilibrium, Proceedings of the National Academy of Sciences of the United States of America, 2014, Vol. 111, No. 3 Supp., pp. 10826-10829 - https://hdl.handle.net/1814/33961

Retrieved from Cadmus, EUI Research Repository

We examine the long-term implication of two models of learning with recency bias: recursive weights and limited memory. We show that both models generate similar beliefs and that both have a weighted universal consistency property. Using the limited-memory model we produce learning procedures that both are weighted universally consistent and converge with probability one to strict Nash equilibrium.

Cadmus permanent link: https://hdl.handle.net/1814/33961

Full-text via DOI: 10.1073/pnas.1400987111

ISSN: 0027-8424

Keyword(s): Normal-form games

Sponsorship and Funder information:

We are grateful to the National Science Foundation (Grants SES-08-51315 and 1258665) for financial support.

Show full item record