Deep Reinforcement Learning with Function Properties in Mean Reversion Strategies

TL;DR

This paper demonstrates how to adapt deep reinforcement learning techniques, originally designed for strategic games, to solve mean reversion trading problems by incorporating economically-motivated function properties, resulting in a high-performance, convergent solution.

Contribution

It introduces a framework that applies game-based DRL libraries to financial trading, integrating economic function properties for improved decision-making in mean reversion strategies.

Findings

High-performance DRL solution for mean reversion trading

Framework successfully incorporates economic function properties

Demonstrates convergence and effectiveness in financial decision-making

Abstract

Over the past decades, researchers have been pushing the limits of Deep Reinforcement Learning (DRL). Although DRL has attracted substantial interest from practitioners, many are blocked by having to search through a plethora of available methodologies that are seemingly alike, while others are still building RL agents from scratch based on classical theories. To address the aforementioned gaps in adopting the latest DRL methods, I am particularly interested in testing out if any of the recent technology developed by the leads in the field can be readily applied to a class of optimal trading problems. Unsurprisingly, many prominent breakthroughs in DRL are investigated and tested on strategic games: from AlphaGo to AlphaStar and at about the same time, OpenAI Five. Thus, in this writing, I want to show precisely how to use a DRL library that is initially built for games in a fundamental trading problem; mean reversion. And by introducing a framework that incorporates economically-motivated function properties, I also demonstrate, through the library, a highly-performant and convergent DRL solution to decision-making financial problems in general.