Right Place, Right Time: Market Simulation-based RL for Execution Optimisation

TL;DR

This paper introduces a reinforcement learning framework for optimizing trade execution strategies within a simulated market environment, effectively balancing market impact and execution risk to outperform traditional methods.

Contribution

It presents a novel RL-based approach for execution optimization evaluated in a realistic market simulator, demonstrating superior performance over baseline strategies.

Findings

RL strategies outperform baselines

Strategies operate near the efficient frontier

Effective risk and impact trade-off achieved

Abstract

Execution algorithms are vital to modern trading, they enable market participants to execute large orders while minimising market impact and transaction costs. As these algorithms grow more sophisticated, optimising them becomes increasingly challenging. In this work, we present a reinforcement learning (RL) framework for discovering optimal execution strategies, evaluated within a reactive agent-based market simulator. This simulator creates reactive order flow and allows us to decompose slippage into its constituent components: market impact and execution risk. We assess the RL agent's performance using the efficient frontier based on work by Almgren and Chriss, measuring its ability to balance risk and cost. Results show that the RL-derived strategies consistently outperform baselines and operate near the efficient frontier, demonstrating a strong ability to optimise for risk and impact. These findings highlight the potential of reinforcement learning as a powerful tool in the trader's toolkit.