Deep graph convolutional reinforcement learning for financial portfolio management – DeepPocket

作者：

Highlights：

• Portfolio management using a deep graph convolutional reinforcement learning method.

• Extracting low-dimensional features using Restricted Stacked Autoencoder.

• Interrelation among financial instruments is obtained using a DeepPocket method.

• An actor-critic framework is exploited to enforce the investment policy.

• The reinforcement learning framework is trained both offline and online.

摘要

•Portfolio management using a deep graph convolutional reinforcement learning method.•Extracting low-dimensional features using Restricted Stacked Autoencoder.•Interrelation among financial instruments is obtained using a DeepPocket method.•An actor-critic framework is exploited to enforce the investment policy.•The reinforcement learning framework is trained both offline and online.

论文关键词：Portfolio management,Deep reinforcement learning,Restricted stacked autoencoder,Online leaning,Actor-critic,Graph convolutional network

论文评审过程：Received 6 August 2020, Revised 12 March 2021, Accepted 24 April 2021, Available online 2 May 2021, Version of Record 26 July 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115127