Showing q-fin.TRShow all
2 papers · 1 filter
q-fin.TR2026
Understanding the Inner Workings of a State-Space Foundation Model for Limit Order Books
Valentin Mohl, Alexandre Bismuth, Aramis Marti-Shahandeh +6
Autoregressive foundation models offer state-of-the-art capabilities to simulate the market by generating the message flow of limit order books (LOBs). Yet, without understanding t…
q-fin.TR2025
JaxMARL-HFT: GPU-Accelerated Large-Scale Multi-Agent Reinforcement Learning for High-Frequency Trading
Valentin Mohl, Sascha Frey, Reuben Leyland +6
Agent-based modelling (ABM) approaches for high-frequency financial markets are difficult to calibrate and validate, partly due to the large parameter space created by defining fix…