An application of deep reinforcement learning to algorithmic trading

作者：

Highlights：

• Reinforcement learning (RL) formalization of the algorithmic trading problem.

• Novel trading strategy based on deep reinforcement learning (DRL), denominated TDQN.

• Rigorous performance assessment methodology for algorithmic trading.

• TDQN algorithm delivers promising results surpassing benchmark strategies.

摘要

•Reinforcement learning (RL) formalization of the algorithmic trading problem.•Novel trading strategy based on deep reinforcement learning (DRL), denominated TDQN.•Rigorous performance assessment methodology for algorithmic trading.•TDQN algorithm delivers promising results surpassing benchmark strategies.

论文关键词：Artificial intelligence,Deep reinforcement learning,Algorithmic trading,Trading policy

论文评审过程：Received 7 April 2020, Revised 13 January 2021, Accepted 17 January 2021, Available online 28 January 2021, Version of Record 23 February 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.114632