Recency, consistent learning, and Nash equilibrium

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 b...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Proceedings of the National Academy of Sciences - PNAS 2014-07, Vol.111 (Supplement 3), p.10826-10829
Hauptverfasser:	Fudenberg, Drew, Levine, David K.
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Approximation Base interest rates Belief & doubt Bias Cognitive models COLLOQUIUM PAPERS Determinism Game Theory Humans In the Light of Evolution VIII: Darwinian Thinking in the Social Sciences Sackler Learning Learning - physiology Learning procedures Memory Memory - physiology Memory, Short-Term - physiology Models, Psychological Nash equilibrium Perceptron convergence procedure Probability Retention (Psychology) - physiology Social Sciences Term weighting Weighted averages
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	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.
ISSN:	0027-8424 1091-6490
DOI:	10.1073/pnas.1400987111