Time-driven feature-aware jointly deep reinforcement learning for financial signal representation and algorithmic trading
作者:
Highlights:
• TFJ-DRL that interactively leverages DL and RL is viable in algorithmic trading.
• The determination of financial signals introduces informative background knowledge.
• Summarizing historical trading data and changing trend aids environmental learning.
摘要
•TFJ-DRL that interactively leverages DL and RL is viable in algorithmic trading.•The determination of financial signals introduces informative background knowledge.•Summarizing historical trading data and changing trend aids environmental learning.
论文关键词:Algorithmic trading,Deep reinforcement learning,Gate,Temporal attention
论文评审过程:Received 24 January 2019, Revised 12 August 2019, Accepted 13 August 2019, Available online 14 August 2019, Version of Record 20 August 2019.
论文官网地址:https://doi.org/10.1016/j.eswa.2019.112872