Towards Generalizable Reinforcement Learning for Trade Execution

TL;DR

This paper investigates overfitting in reinforcement learning for trade execution, models it as offline RL with dynamic context, and proposes compact representation learning to improve generalization, validated through a high-fidelity simulator.

Contribution

It introduces a formal framework for trade execution as offline RL with dynamic context and proposes methods to mitigate overfitting via compact context representations.

Findings

Proposed a theoretical generalization bound highlighting overfitting causes.

Developed algorithms that learn compact context representations to reduce overfitting.

Experiments show improved performance and generalization in a high-fidelity simulator.

Abstract

Optimized trade execution is to sell (or buy) a given amount of assets in a given time with the lowest possible trading cost. Recently, reinforcement learning (RL) has been applied to optimized trade execution to learn smarter policies from market data. However, we find that many existing RL methods exhibit considerable overfitting which prevents them from real deployment. In this paper, we provide an extensive study on the overfitting problem in optimized trade execution. First, we model the optimized trade execution as offline RL with dynamic context (ORDC), where the context represents market variables that cannot be influenced by the trading policy and are collected in an offline manner. Under this framework, we derive the generalization bound and find that the overfitting issue is caused by large context space and limited context samples in the offline setting. Accordingly, we propose to learn compact representations for context to address the overfitting problem, either by leveraging prior knowledge or in an end-to-end manner. To evaluate our algorithms, we also implement a carefully designed simulator based on historical limit order book (LOB) data to provide a high-fidelity benchmark for different algorithms. Our experiments on the high-fidelity simulator demonstrate that our algorithms can effectively alleviate overfitting and achieve better performance.