linear-function-approximation

This paper proposes efficient online learning algorithms for policy evaluation in MDPs with dynamic utility-based shortfall risk (UBSR) measures under linear function approximation, introducing the UBSR-TD algorithm and demonstrating its convergence and practical effectiveness.

This paper presents a switching-system theory for Q-learning with linear function approximation, using joint spectral radius to analyze convergence stability under deterministic, i.i.d., and Markovian observations.