Information flow in learning a coin-tossing game

• Sato Yuzuru

  RIES / Department of Mathematics, Hokkaido Univeristy London Mathematical Laboratory

• Ay Nihat

  Max Planck Institute for Mathematics in the Sciences Santa Fe Institute Faculty of Mathematics and Computer Science, University of Leipzig

抄録

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.

収録刊行物

• Nonlinear Theory and Its Applications, IEICE

  Nonlinear Theory and Its Applications, IEICE 7 (2), 118-125, 2016

  一般社団法人 電子情報通信学会

キーワード

• game dynamics
• information theory
• dynamical systems

詳細情報

• CRID: 1390282680321040512
• NII論文ID: 130005142575
• DOI: 10.1587/nolta.7.118
• ISSN: 21854106
• HANDLE: 2115/65395
• Web Site: https://www.jstage.jst.go.jp/article/nolta/7/2/7_118/_pdf
• 本文言語コード: en
• データソース種別:
  • JaLC
  • IRDB
  • Crossref
  • CiNii Articles
  • KAKEN
• 抄録ライセンスフラグ: 使用不可