Similar Search Results

Learnability of a class of Non-atomic Games arising on the Internet

Friedman, Eric - 1998

learnable by several models of learning, such as adaptive and sophisticated learning (Milgrom and Roberts 1991), calibrated … learning (Foster and Vohra 1996), and reasonable learning (Friedman and Shenker 1997). Thus, using these methods one can …

Persistent link: https://www.econbiz.de/10010334330

Learning in Networks Contexts: Experimental Results from Simulations

Friedman, Eric; Shenker, Scott; Greenwald, Amy - 1998

This paper describes the results of simulation experiments performed on a suite of learning algorithms. We focus on … be extremely asynchronous; players update their strategies at very different rates. There are many proposed learning … information, asynchronous play, and the degree of responsiveness of the learning algorithm. …

Persistent link: https://www.econbiz.de/10010334347

Learning and Implementation on the Internet

Friedman, Eric; Shenker, Scott - 1998

We address the problem of learning and implementation on the Internet. When agents play repeated games in distributed … the essential properties that constitute ``reasonable'' learning behavior in distributed environments. We then study the …

Persistent link: https://www.econbiz.de/10010334355

Education, Cognition, Health Knowledge, and Health Behavior

Mocan, Naci; Altindag, Duha T. - 2013

education on health behavior is the same between those with and without a learning disability, suggesting that cognition is not …

Persistent link: https://www.econbiz.de/10010500243

An experiment on learning with limited information: Nonconvergence, experimentation cascades, and the advantage of being slow

Friedman, Eric; Shor, Mikhael; Shenker, Scott; Sopher, Barry - 2000

We present the results of an experiment on learning in a continuous-time low-information setting. For a Cournot …

Persistent link: https://www.econbiz.de/10010318349

When is tit-for-tat unbeatable?

Duersch, Peter; Oechssler, Joerg; Schipper, Burkhard C. - 2013

We characterize the class of symmetric two-player games in which tit-for-tat cannot be beaten even by very sophisticated opponents in a repeated game. It turns out to be the class of exact potential games. More generally, there is a class of simple imitation rules that includes tit-for-tat but...

Persistent link: https://www.econbiz.de/10010318837

Once beaten, never again: Imitation in two-player potential games

Duersch, Peter; Oechssler, Joerg; Schipper, Burkhard C. - 2011

We show that in symmetric two-player exact potential games, the simple decision rule imitate-if-better cannot be beaten by any strategy in a repeated game by more than the maximal payoff difference of the one-period game. Our results apply to many interesting games including examples like 2x2...

Persistent link: https://www.econbiz.de/10010282072

Unbeatable imitation

Duersch, Peter; Oechssler, Joerg; Schipper, Burkhard C. - 2012

We show that for many classes of symmetric two-player games, the simple decision rule 'imitate-if-better' can hardly be beaten by any strategy. We provide necessary and sufficient conditions for imitation to be unbeatable in the sense that there is no strategy that can exploit imitation as a...

Persistent link: https://www.econbiz.de/10010282081