Linear learning in changing environments

DOI10.1016/J.JEDC.2005.08.007MaRDI QIDQ959694zbMATH OpenOpenAlexFDO

Authors Tilman Klumpp

Publication date 12 December 2008

Published in Journal of Economic Dynamics and Control (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.jedc.2005.08.007

zbMATH Keywords

bounded rationalitychanging environmentsevolution of learning rulesexponential smoothing rulelearning

Mathematics Subject Classification ID

Bayesian problems; characterization of Bayes procedures (62C10) Rationality and learning in game theory (91A26)

Recommendations

• Expedient and Monotone Learning Rules
• An evolutionary approach to learning in a changing environment.
• Learning and control in a changing economic environment.
• Optimal learning with costly adjustment
• Bayesian approximations and extensions: optimal decisions for small brains and possibly big ones too

Cites work

• A Rational Route to Randomness
• Agent-based computational finance: Suggested readings and early research
• Economists' models of learning
• scientific article; zbMATH DE number 3137856 (Why is no real title available?)
• scientific article; zbMATH DE number 4078557 (Why is no real title available?)
• scientific article; zbMATH DE number 1281936 (Why is no real title available?)
• scientific article; zbMATH DE number 3109895 (Why is no real title available?)
• Learning about variable demand in the long run
• Learning and control in a changing economic environment.
• On the relationship between mutation rates and growth rates in a changing environment
• Optimal Experimentation in a Changing Environment
• Optimal Properties of Exponentially Weighted Forecasts
• Periodic learning about a hidden state variable
• Social learning in a changing world

Cited in

(12)

• Nonlinear versus linear learning devices: A procedural perspective
• Bayesian approximations and extensions: optimal decisions for small brains and possibly big ones too
• Can natural selection encode Bayesian priors?
• Optimal learning with costly adjustment
• Novelty detection improves performance of reinforcement learners in fluctuating, partially observable environments
• Optimal guessing: choice in complex environments
• A note on absolutely expedient learning rules
• Learning algorithms based on linearization
• Mean and variance responsive learning
• Sequential learning versus no learning in Bayesian regression models
• On learning and testing dynamic environments
• Expedient and Monotone Learning Rules

Describes a project that uses

Uses Software

• BayesDA

This page was built for publication: Linear learning in changing environments

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q959694)