Similar Search Results

Rage Against the Machines: How Subjects Learn to Play Against Computers

Dürsch, Peter; Kolb, Albert; Oechssler, Jörg; … - 2005

number of standard learning algorithms. The learning theories are (unbeknown to subjects) a best response process, fictitious … play, imitation, reinforcement learning, and a trial & error process. We test whether subjects try to influence those … and that all learning algorithms are subject to exploitation with the notable exception of imitation. The experiment was …

Persistent link: https://www.econbiz.de/10011422135

Unbeatable Imitation

Duersch, Peter; Oechssler, Jörg; Schipper, Burkhard C. - 2010

We show that for many classes of symmetric two-player games, the simple decision rule "imitate-the-best" can hardly be beaten by any other decision rule. We provide necessary and sufficient conditions for imitation to be unbeatable and show that it can only be beaten by much in games that are of...

Persistent link: https://www.econbiz.de/10011422207

Rage Against the Machines: How Subjects Learn to Play Against Computers

Dürsch, Peter; Kolb, Albert; Oechssler, Jörg; … - 2005

Persistent link: https://www.econbiz.de/10010333843

Rage Against the Machines: How Subjects Learn to Play Against Computers

Dürsch, Peter; Kolb, Albert; Oechssler, Jörg; … - 2005

Persistent link: https://www.econbiz.de/10010263153

Once Beaten, Never Again: Imitation in Two-Player Potential Games

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

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/10011422230

Loss of commitment? An evolutionary analysis of Bagwell's example

Oechssler, Jörg; Schlag, Karl H. - 1997

of evolutionary and learning processes in this game. Only the continuous best response dynamic uniquely selects the …

Persistent link: https://www.econbiz.de/10010310808

Through Trial & Error to Collusion - The Discrete Case

Huck, Steffen; Normann, Hans-Theo; Oechssler, Jörg - 2000

In this note we study a very simple trial & error learning process in the context of a Cournot oligopoly. Without any …

Persistent link: https://www.econbiz.de/10010317631

Can You Guess the Game You're Playing?

Oechssler, Jörg; Schipper, Burkhard C. - 2000

Recently there has been much theoretical and experimental work on learning in games. However, learning usually means … "learning about the strategic behavior of opponents" rather than "learning about the game" as such. In contrast, here we report …

Persistent link: https://www.econbiz.de/10010317675

Unbeatable imitation

Duersch, Peter; Oechssler, Jörg; Schipper, Burkhard C. - 2010

We show that for many classes of symmetric two-player games, the simple decision rule imitate-the-best can hardly be beaten by any other decision rule. We provide necessary and sufficient conditions for imitation to be unbeatable and show that it can only be beaten by much in games that are of...

Persistent link: https://www.econbiz.de/10010282117

When is tit-for-tat unbeatable?

Duersch, Peter; Oechssler, Jörg; Schipper, Burkhard - In: International Journal of Game Theory 43 (2014) 1, pp. 25-36

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/10010993382