Nonlinear Theory and Its Applications, IEICE
Online ISSN : 2185-4106
Special Section on Recent Progress in Nonlinear Dynamics in Biological Systems
Information flow in learning a coin-tossing game
Yuzuru SatoNihat Ay
Author information
JOURNALS FREE ACCESS

2016 Volume 7 Issue 2 Pages 118-125

Details
Abstract

Information flow in adaptively interacting stochastic processes is studied. We give an extended form of game dynamics for interacting Markovian processes and compute a measure of causal information flow, which is different from the transfer entropy. In the game theoretic situation, causal information flow can show oscillatory behavior through reward-maximizing adaptation of two players. The adaptive dynamics for the coin-tossing game is exemplified and the causal information flow therein is investigated.

Information related to the author
© 2016 The Institute of Electronics, Information and Communication Engineers
Previous article Next article
feedback
Top