Double Deep Q-Learning for Optimal Execution. Issue 4 (4th July 2021)

• Record Type: Journal Article
• Authors: Ning, Brian; Lin, Franco Ho Ting; Jaimungal, Sebastian
• Is Part Of: Applied mathematical finance. Volume 28:Issue 4(2021)
• Page Start: 361
• Page End: 380
• Publication Date: 2021-07-04
• Subjects: algorithmic trading -- reinforcement learning -- optimal execution -- DDQN; Business mathematics -- Periodicals; 650.0151
• DOI: 10.1080/1350486X.2022.2077783
• Languages: English
• ISSNs: 1350-486X

Abstract

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.