Optimizing Automated Trading Systems Portfolios with Reinforcement Learning for Risk Control

Abstract

This work proposes an innovative method for optimizing Automated Trading Systems (ATS) portfolios with advanced Deep Reinforcement Learning (DRL) techniques. The algorithms A2C, DDPG, PPO, SAC, and TD3 are assessed for their ability to learn and adapt in volatile market conditions. The main goal is to enhance ATS's risk control and operational efficiency using data from the Brazilian stock market. DRL models outperformed traditional benchmarks by offering better risk management and risk-adjusted returns. The findings demonstrate the potential of DRL algorithms in complex financial scenarios and lay the groundwork for future research on integrating machine learning in quantitative finance.