Optimization of Stock Trading System based on Multi-Agent Q-Learning Framework


The KIPS Transactions:PartB , Vol. 11, No. 2, pp. 207-212, Apr. 2004
10.3745/KIPSTB.2004.11.2.207,   PDF Download:

Abstract

This paper presents a reinforcement learning framework for stock trading systems. Trading system parameters are optimized by Q-learning algorithm and neural networks are adopted for value approximation. In this framework, cooperative multiple agents are used to efficiently integrate global trend prediction and local trading strategy for obtaining better trading performance. Agents communicate with others sharing training episodes and learned policies, while keeping the overall scheme of conventional Q-learning. Experimental results on KOSPI 200 show that a trading system based on the proposed framework outperforms the market average and makes appreciable profits. Furthermore, in view of risk management, the system is superior to a system trained by supervised learning.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
K. Y. Seob, L. J. Won, L. J. U, "Optimization of Stock Trading System based on Multi-Agent Q-Learning Framework," The KIPS Transactions:PartB , vol. 11, no. 2, pp. 207-212, 2004. DOI: 10.3745/KIPSTB.2004.11.2.207.

[ACM Style]
Kim Yu Seob, Lee Jae Won, and Lee Jong U. 2004. Optimization of Stock Trading System based on Multi-Agent Q-Learning Framework. The KIPS Transactions:PartB , 11, 2, (2004), 207-212. DOI: 10.3745/KIPSTB.2004.11.2.207.