The Evolution of Algorithmic Learning Rules : A Global Stability Result.

This paper considers the dynamic evolution of algorithmic (recursive) learning rules in a normal form game. It is shown that the system - the population frequencies - is globally stable for any arbitrary N-player normal form game, if the evolutionary process is algorithmic and the "birth process" guarantees that an appropriate set of "smart" rules is present in the population.

MoreLess

Year of publication:	1996
Authors:	Anderlini, L ; Sabourian, H
Institutions:	Department of Economics, European University Institute
Subject:	ECONOMETRICS \| LEARNING

Check Google Scholar |

More access options

In German libraries (KVK)

I need help

More details

Series:	Economics Working Papers.
Type of publication:	Book / Working Paper
Notes:	52 pages
Classification:	C70 - Game Theory and Bargaining Theory. General ; C72 - Noncooperative Games ; C79 - Game Theory and Bargaining Theory. Other ; D83 - Search, Learning, Information and Knowledge
Source:	RePEc - Research Papers in Economics

Persistent link: https://www.econbiz.de/10005816361