Logic-Q: Improving Deep Reinforcement Learning-based Quantitative Trading via Program Sketch-based Tuning

TL;DR

Logic-Q enhances deep reinforcement learning for quantitative trading by integrating human expert knowledge through program sketches, leading to significant performance improvements in market trend detection and trading strategies.

Contribution

The paper introduces a novel logic-guided framework that incorporates abstract human knowledge into DRL models via program sketching for improved trading performance.

Findings

Logic-Q outperforms previous DRL trading strategies.

Incorporating program sketches improves market trend detection.

Significant performance gains in quantitative trading tasks.

Abstract

Deep reinforcement learning (DRL) has revolutionized quantitative trading (Q-trading) by achieving decent performance without significant human expert knowledge. Despite its achievements, we observe that the current state-of-the-art DRL models are still ineffective in identifying the market trends, causing them to miss good trading opportunities or suffer from large drawdowns when encountering market crashes. To address this limitation, a natural approach is to incorporate human expert knowledge in identifying market trends. Whereas, such knowledge is abstract and hard to be quantified. In order to effectively leverage abstract human expert knowledge, in this paper, we propose a universal logic-guided deep reinforcement learning framework for Q-trading, called Logic-Q. In particular, Logic-Q adopts the program synthesis by sketching paradigm and introduces a logic-guided model design that leverages a lightweight, plug-and-play market trend-aware program sketch to determine the market trend and correspondingly adjusts the DRL policy in a post-hoc manner. Extensive evaluations of two popular quantitative trading tasks demonstrate that Logic-Q can significantly improve the performance of previous state-of-the-art DRL trading strategies.