Hokkaido University Collection of Scholarly and Academic Papers >
Research Institute for Electronic Science >
Peer-reviewed Journal Articles, etc >
Information flow in learning a coin-tossing game
Title: | Information flow in learning a coin-tossing game |
Authors: | Sato, Yuzuru Browse this author →KAKEN DB | Ay, Nihat Browse this author |
Keywords: | game dynamics | information theory | dynamical systems |
Issue Date: | 1-Apr-2016 |
Publisher: | 電子情報通信学会 |
Journal Title: | IEEE Nonlinear Theory and its Applications |
Volume: | 7 |
Issue: | 2 |
Start Page: | 118 |
End Page: | 125 |
Publisher DOI: | 10.1587/nolta.7.118 |
Abstract: | Information flow in adaptively interacting stochastic processes is studied. We give an extended form of game dynamics for interactingMarkovian 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. |
Rights: | Copyright © 2016 The Institute of Electronics, Information and Communication Engineers |
Relation: | http://search.ieice.org/ |
Type: | article |
URI: | http://hdl.handle.net/2115/65395 |
Appears in Collections: | 電子科学研究所 (Research Institute for Electronic Science) > 雑誌発表論文等 (Peer-reviewed Journal Articles, etc)
|
Submitter: 佐藤 譲
|