JaxMARL-HFT: GPU-Accelerated Large-Scale Multi-Agent Reinforcement Learning for High-Frequency Trading

By Valentin Mohl, Sascha Frey, Reuben Leyland, Kang Li, George Nigmatulin, Mihai Cucuringu, Stefan Zohren, Jakob Foerster, Anisoara Calinescu

Published 2025-11-03

Everscope rating

1845.5

Relevance to quantitative trading

9 / 10

Implementation complexity

7 / 10

Reproducibility

5 / 5

About this paper

Methodology: JaxMARL-HFT: GPU-Accelerated Multi-Agent Reinforcement Learning Environment. Problem types: Reinforcement Learning, Market Making, Algorithmic Execution, Multi-agent Simulation, Optimization.

arXiv:2511.02136 · Code · Paper rankings

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