Deep differentiable reinforcement learning and optimal trading

DOI10.1080/14697688.2022.2062431MaRDI QIDQ5092657zbMATH OpenOpenAlexFDO

Authors Thibault Jaisson

Publication date 22 July 2022

Published in Quantitative Finance (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2112.02944

zbMATH Keywords

deep learningdifferentiabledynamic programmingmulti-scale signalsoptimal tradingreinforcement learningstochastic control

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Financial markets (91G15) Optimal stochastic control (93E20)

Abstract: In many reinforcement learning applications, the underlying environment reward and transition functions are explicitly known differentiable functions. This enables us to use recent research which applies machine learning tools to stochastic control to find optimal action functions. In this paper, we define differentiable reinforcement learning as a particular case of this research. We find that incorporating deep learning in this framework leads to more accurate and stable solutions than those obtained from more generic actor critic algorithms. We apply this deep differentiable reinforcement learning (DDRL) algorithm to the problem of one asset optimal trading strategies in various environments where the market dynamics are known. Thanks to the stability of this method, we are able to efficiently find optimal strategies for complex multi-scale market models. We also extend these methods to simultaneously find optimal action functions for a wide range of environment parameters. This makes it applicable to real life financial signals and portfolio optimization where the expected return has multiple time scales. In the case of a slow and a fast alpha signal, we find that the optimal trading strategy consists in using the fast signal to time the trades associated to the slow signal.

Recommendations

• Double deep Q-learning for optimal execution
• A reinforcement learning approach to optimal execution
• Deep hedging
• Deep reinforcement learning for the optimal placement of cryptocurrency limit orders
• Meta algorithms for portfolio optimization using reinforcement learning

Cites work

• \({\mathcal Q}\)-learning
• An introduction to deep reinforcement learning
• Autoencoder asset pricing models
• Deep learning volatility: a deep neural network perspective on pricing and calibration in (rough) volatility models
• Dynamic programming and optimal control. Vol. 2
• Neural networks-based backward scheme for fully nonlinear PDEs
• Optimal execution with non-linear transient market impact
• Reinforcement learning. An introduction

Cited in

(5)

• Learning to profit with discrete investment rules
• scientific article; zbMATH DE number 7113167 (Why is no real title available?)
• Foundations of Reinforcement Learning with Applications in Finance
• Reinforcement Learning for Optimal Execution When Liquidity Is Time-Varying
• Heterogeneous trading strategies with adaptive fuzzy actor-critic reinforcement learning: a behavioral approach

This page was built for publication: Deep differentiable reinforcement learning and optimal trading

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5092657)