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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Zhiming, Jiang, Junzhe, Cao, Yushi, Cui, Aixin, Wu, Bozhi, Li, Bo, Liu, Yang, Sun, Danny Dongning
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929699287990272
author Li, Zhiming
Jiang, Junzhe
Cao, Yushi
Cui, Aixin
Wu, Bozhi
Li, Bo
Liu, Yang
Sun, Danny Dongning
author_facet Li, Zhiming
Jiang, Junzhe
Cao, Yushi
Cui, Aixin
Wu, Bozhi
Li, Bo
Liu, Yang
Sun, Danny Dongning
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2310_05551
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Logic-Q: Improving Deep Reinforcement Learning-based Quantitative Trading via Program Sketch-based Tuning
Li, Zhiming
Jiang, Junzhe
Cao, Yushi
Cui, Aixin
Wu, Bozhi
Li, Bo
Liu, Yang
Sun, Danny Dongning
Computational Engineering, Finance, and Science
Artificial Intelligence
Programming Languages
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.
title Logic-Q: Improving Deep Reinforcement Learning-based Quantitative Trading via Program Sketch-based Tuning
topic Computational Engineering, Finance, and Science
Artificial Intelligence
Programming Languages
url https://arxiv.org/abs/2310.05551