An Algorithm for Trading and Portfolio Management Using Q-learning and Sharpe Ratio Maximization
暂无分享,去创建一个
A trading and portfolio management system called QSR is proposed. It uses Q-learning and Sharpe ratio maximization algorithm. We use absolute proot and relative risk-adjusted proot as performance function to train the system respectively, and employ a committee of two networks to do the testing. The new proposed algorithm makes use of the advantages of both parts and can be used in a more general case. We demonstrate with experimental results that the proposed approach generates appreciable proots from trading in the foreign exchange markets.
[1] Ben J. A. Kröse,et al. Learning from delayed rewards , 1995, Robotics Auton. Syst..
[2] Andreas S. Weigend,et al. Nonlinear Trading Models Through Sharpe Ratio Maximization , 1997, Int. J. Neural Syst..
[3] Nien Fan Zhang,et al. Forecasting and time series analysis , 1976 .
[4] Stephen Taylor,et al. Forecasting Economic Time Series , 1979 .
[5] Ralph Neuneier,et al. Optimal Asset Allocation using Adaptive Dynamic Programming , 1995, NIPS.