A Q-learning agent for automated trading in equity stock markets

作者：

Highlights：

• Generated optimal dynamic trading strategies using Reinforcement Learning.

• Clusters used to represent states which implicitly embeds domain knowledge.

• Trained Q-learning agent to make automated trading decisions.

• Comparative analysis of model on stocks of various trends.

摘要

•Generated optimal dynamic trading strategies using Reinforcement Learning.•Clusters used to represent states which implicitly embeds domain knowledge.•Trained Q-learning agent to make automated trading decisions.•Comparative analysis of model on stocks of various trends.

论文关键词：Reinforcement Learning,Algorithmic trading,Stock market

论文评审过程：Received 28 February 2020, Revised 22 June 2020, Accepted 12 July 2020, Available online 2 August 2020, Version of Record 6 August 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113761