A Hierarchical Reinforcement Learning Framework for Stock Selection and Portfolio

Abstract

Investment is a common economics task in which investors maximize future profits by continuously reallocating their current assets. A large number of studies are based on specifying stocks and constantly adjusting the ratio between these stocks to gain more benefits. However, the question of which stocks should be included in the portfolio is not addressed, while some investment strategies only select stocks and buy them without portfolio optimization, which may also cause unexpected loss owing to market oscillation. We try to integrate stock selection and portfolio optimization as a complete process to address this problem using hierarchical reinforcement learning. The high-level policy selects stocks with a high profitable probability, and then the low-level policy makes portfolio optimization on the selected stocks to gain more profit. The performance in China market demonstrates that our hierarchical agents can over performance a single stock selection agent.