Loading...

A Multi-agent Deep Reinforcement Learning Framework for Algorithmic Trading in Financial Markets

Shavandi, Ali | 2022

180 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 54909 (01)
  4. University: Sharif University of Technology
  5. Department: Industrial Engineering
  6. Advisor(s): Khedmati, Majid
  7. Abstract:
  8. Algorithmic trading in financial markets with machine learning is a developing and promising field of research. Financial markets have a complex, uncertain, and dynamic nature, making them challenging for algorithmic trading. To cope with the challenges of algorithmic trading in financial markets, we propose a multi-agent deep reinforcement learning framework trained by Deep Q-learning (DQN) algorithm to perform financial trading. This framework consists of multiple cooperative agents, each of which trained on a specific timeframe, to perform financial trading on the collective intelligence of the agents. Numerical experiments are conducted on historical data of the EUR/USD currency pair. The results demonstrate that the proposed multi-agent framework outperforms single independent agents in all timeframes. Furthermore, the proposed framework outperforms some basic trading strategies such as Buy and Hold, MACD, RSI, and Moving Average Cross according to several financial performance metrics, such as average annual return, maximum drawdown, and win rate. The robust performance of the multi-agent framework throughout the trading period makes it suitable for algorithmic trading in financial markets
  9. Keywords:
  10. Reinforcement Learning ; Algorithmic Trading ; Multi-Agent Reinforcement Learning ; Deep Q-Network (DQN)Algorithm ; Financial Market ; Multi-Timeframe

 Digital Object List

 Bookmark

No TOC