Scholarlink

To date, few studies have investigated the application of reinforcement learning methods in algorithmic stock trading. This study aims to address this gap by conducting a systematic literature review using a lightweight PRISMA protocol. Two findings emerged from our research. First, we identified nine different Reinforcement Learning (RL) used in stock trading. The most widely used RL methods are the Deep Q-Network (DQN), Proximal Policy Optimization (PPO), Advantage Actor-Critic (A2C), Twin Delayed DDPG (TD3), and Soft Actor-Critic (SAC). Second, we determined sixteen performance evaluation measures. The most popular measures are the Sharpe ratio, Cumulative return, Annual return, Maximum Drawdown (MDD), and Sortino ratio. We believe these results could be useful for both the research community and novice stock traders. In the future, we will investigate the effectiveness of selected trading strategies in bull and bear markets.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A Review of Reinforcement Learning Methods and Performance Measures in Algorithmic Stock Trading

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Aleksander Kruczkowski,
  • Paweł Weichbroth

摘要

To date, few studies have investigated the application of reinforcement learning methods in algorithmic stock trading. This study aims to address this gap by conducting a systematic literature review using a lightweight PRISMA protocol. Two findings emerged from our research. First, we identified nine different Reinforcement Learning (RL) used in stock trading. The most widely used RL methods are the Deep Q-Network (DQN), Proximal Policy Optimization (PPO), Advantage Actor-Critic (A2C), Twin Delayed DDPG (TD3), and Soft Actor-Critic (SAC). Second, we determined sixteen performance evaluation measures. The most popular measures are the Sharpe ratio, Cumulative return, Annual return, Maximum Drawdown (MDD), and Sortino ratio. We believe these results could be useful for both the research community and novice stock traders. In the future, we will investigate the effectiveness of selected trading strategies in bull and bear markets.