Reinforcement Learning in Queue-Reactive Models: Application to Optimal Execution

TL;DR

This paper demonstrates that model-free Reinforcement Learning, specifically using a Double Deep Q-Network, can effectively optimize large order execution by adapting to market conditions and outperforming traditional methods.

Contribution

It introduces a novel application of Reinforcement Learning with a Queue-Reactive Model for realistic limit order book simulation in optimal execution tasks.

Findings

RL agent outperforms benchmarks in simulations

The approach adapts to dynamic market conditions

Model-free RL provides robust execution strategies

Abstract

We investigate the use of Reinforcement Learning for the optimal execution of meta-orders, where the objective is to execute incrementally large orders while minimizing implementation shortfall and market impact over an extended period of time. Departing from traditional parametric approaches to price dynamics and impact modeling, we adopt a model-free, data-driven framework. Since policy optimization requires counterfactual feedback that historical data cannot provide, we employ the Queue-Reactive Model to generate realistic and tractable limit order book simulations that encompass transient price impact, and nonlinear and dynamic order flow responses. Methodologically, we train a Double Deep Q-Network agent on a state space comprising time, inventory, price, and depth variables, and evaluate its performance against established benchmarks. Numerical simulation results show that the agent learns a policy that is both strategic and tactical, adapting effectively to order book conditions and outperforming standard approaches across multiple training configurations. These findings provide strong evidence that model-free Reinforcement Learning can yield adaptive and robust solutions to the optimal execution problem.