Learning in games with bounded memory

Learning in games with bounded memory

0.00 Avg rating0 Votes
Article ID: iaor2009591
Country: Poland
Volume: 35
Issue: 2
Start Page Number: 303
End Page Number: 333
Publication Date: Jan 2006
Journal: Control and Cybernetics
Authors:
Keywords: learning
Abstract:

The paper studies infinite repetition of finite strategic form games. Players use a backward looking learning behaviour and face bounds on their cognitive capacities. We show that for any given belief-probability over the set of possible outcomes, where players have no experience, games can be payoff classified and there always exists a stationary state in the space of action profiles. In particular, if the belief-probability assumes all possible outcomes without experience to be equally likely, in one class of Prisoners' Dilemmas, where the uniformly weighted average defecting payoff is higher than the cooperative payoff and the uniformly weighted average cooperative payoff is lower than the defecting payoff, play converges in the long run to the static Nash equilibrium, while in the other class of Prisoners' Dilemmas, where the reverse holds, play converges to cooperation.

Reviews

Required fields are marked *. Your email address will not be published.