Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/248736 
Year of Publication: 
2021
Series/Report no.: 
Deutsche Bundesbank Discussion Paper No. 51/2021
Publisher: 
Deutsche Bundesbank, Frankfurt a. M.
Abstract: 
This paper introduces a reinforcement learning based approach to compute optimal interest rate reaction functions in terms of fulfilling inflation and output gap targets. The method is generally flexible enough to incorporate restrictions like the zero lower bound, nonlinear economy structures or asymmetric preferences. We use quarterly U.S. data from1987:Q3-2007:Q2 to estimate (nonlinear) model transition equations, train optimal policies and perform counterfactual analyses to evaluate them, assuming that the transition equations remain unchanged. All of our resulting policy rules outperform other common rules as well as the actual federal funds rate. Given a neural network representation of the economy, our optimized nonlinear policy rules reduce the central bank's loss by over43 %. A DSGE model comparison exercise further indicates robustness of the optimized rules.
Subjects: 
Optimal Monetary Policy
Reinforcement Learning
Artificial Neural Network
Machine Learning
Reaction Function
JEL: 
C45
C61
E52
E58
ISBN: 
978-3-95729-861-4
Document Type: 
Working Paper

Files in This Item:
File
Size





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.