A Q-Learning Approach to Derive Optimal Consumption and Investment Strategies

IEEE Transactions on Neural Networks, 2009, 20(8), 1234-1243

31 Pages Posted: 15 Feb 2008 Last revised: 1 Jul 2017

Date Written: February 12, 2008

Abstract

In this paper we consider optimal consumption and strategic asset allocation decisions of an investor with a finite planning horizon. A Q-learning approach is used to maximize the expected utility of consumption. The first part of the paper presents conceptually the implementation of Q-learning in a discrete state-action space and relates the technique to the dynamic programming method. An illustrative example is given in a simplified setting. In the second part of the paper different generalization methods are explored and, compared to other implementations using neural networks, a combination with self-organizing maps is proposed. The resulting, learned policy is compared to other strategies.

Keywords: Dynamic Programming, Reinforcement Learning, Q-learning, Self-organizing Maps, Finance, Asset Allocation

JEL Classification: C44, C45, G11

Suggested Citation

Weissensteiner, Alex, A Q-Learning Approach to Derive Optimal Consumption and Investment Strategies (February 12, 2008). IEEE Transactions on Neural Networks, 2009, 20(8), 1234-1243. Available at SSRN: https://ssrn.com/abstract=1092574

Alex Weissensteiner (Contact Author)

Free University of Bolzano Bozen ( email )

Universitätsplatz 1
Bolzano, 39100
+39 0471 013496 (Phone)

Register to save articles to
your library

Register

Paper statistics

Downloads
131
Abstract Views
665
rank
218,131
PlumX Metrics