Arbeitspapier

Learning and Implementation on the Internet

We address the problem of learning and implementation on the Internet. When agents play repeated games in distributed environments like the Internet, they have very limited {\em a priori} information about the other players and the payoff matrix, and the play can be highly asynchronous. Consequently, standard solution concepts like Nash equilibria, or even the serially undominated set, do not apply in such a setting. To construct more appropriate solution concepts, we first describe the essential properties that constitute ``reasonable'' learning behavior in distributed environments. We then study the convergence behavior of such algorithms; these results lead us to propose rather non traditional solutions concepts for this context. Finally, we discuss implementation of social choice functions with these solution concepts.

Language
Englisch

Bibliographic citation
Series: Working Paper ; No. 1998-21

Classification
Wirtschaft
Noncooperative Games
Search; Learning; Information and Knowledge; Communication; Belief; Unawareness
Subject
Implementation
Internet
Learning

Event
Geistige Schöpfung
(who)
Friedman, Eric
Shenker, Scott
Event
Veröffentlichung
(who)
Rutgers University, Department of Economics
(where)
New Brunswick, NJ
(when)
1998

Handle
Last update
10.03.2025, 11:43 AM CET

Data provider

This object is provided by:
ZBW - Deutsche Zentralbibliothek für Wirtschaftswissenschaften - Leibniz-Informationszentrum Wirtschaft. If you have any questions about the object, please contact the data provider.

Object type

  • Arbeitspapier

Associated

  • Friedman, Eric
  • Shenker, Scott
  • Rutgers University, Department of Economics

Time of origin

  • 1998

Other Objects (12)