Enhancing Q-Learning for Optimal Asset Allocation

Part of Advances in Neural Information Processing Systems 10 (NIPS 1997)

Bibtex Metadata Paper


Ralph Neuneier


This paper enhances the Q-Iearning algorithm for optimal asset alloca(cid:173) tion proposed in (Neuneier, 1996 [6]). The new formulation simplifies the approach by using only one value-function for many assets and al(cid:173) lows model-free policy-iteration. After testing the new algorithm on real data, the possibility of risk management within the framework of Markov decision problems is analyzed. The proposed methods allows the construction of a multi-period portfolio management system which takes into account transaction costs, the risk preferences of the investor, and several constraints on the allocation.