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

By Tomas Espana, Yadh Hafsi, Fabrizio Lillo, Edoardo Vittori

Published 2025-11-20

Everscope rating

1746.1

Relevance to quantitative trading

9 / 10

Implementation complexity

6 / 10

Reproducibility

3 / 5

About this paper

Methodology: Double Deep Q-Network (DDQN) trained in Queue-Reactive Model (QRM) environment. Problem types: Reinforcement Learning, Optimization, Algorithmic Execution, Sequential Decision Making, Stochastic Control.

arXiv:2511.15262 · Paper rankings

Open the interactive Everscope explorer for full analysis, charts, and paper battles.