Double Deep Q-Learning for Optimal Execution

TL;DR

This paper introduces a model-free Deep Q-Learning approach for optimal trade execution, leveraging neural networks and experience replay to outperform traditional methods across multiple stocks.

Contribution

It develops a novel Deep Q-Learning framework for optimal execution that does not rely on model assumptions, using neural networks with experience replay and Double DQN.

Findings

Outperforms benchmark methods on most stocks

Achieves higher mean and median out-performance

Increases probability of out-performance and gain-loss ratios

Abstract

Optimal trade execution is an important problem faced by essentially all traders. Much research into optimal execution uses stringent model assumptions and applies continuous time stochastic control to solve them. Here, we instead take a model free approach and develop a variation of Deep Q-Learning to estimate the optimal actions of a trader. The model is a fully connected Neural Network trained using Experience Replay and Double DQN with input features given by the current state of the limit order book, other trading signals, and available execution actions, while the output is the Q-value function estimating the future rewards under an arbitrary action. We apply our model to nine different stocks and find that it outperforms the standard benchmark approach on most stocks using the measures of (i) mean and median out-performance, (ii) probability of out-performance, and (iii) gain-loss ratios.