3 papers
math.OC2026
Q-Learning under Finite Model Uncertainty
Julian Sester, Cécile Decker
We propose a robust Q-learning algorithm for Markov decision processes under model uncertainty when each state-action pair is associated with a finite ambiguity set of candidate tr…
q-fin.MF2025
Generative modelling of financial time series with structured noise and MMD-based signature learning
Chung I Lu, Julian Sester
Generating synthetic financial time series data that accurately reflects real-world market dynamics holds tremendous potential for various applications, including portfolio optimiz…
cs.LG2025
Distributionally Robust Deep Q-Learning
Chung I Lu, Julian Sester, Aijia Zhang
We propose a novel distributionally robust -learning algorithm for the non-tabular case accounting for continuous state spaces where the state transition of the underlying Marko…