Ankur Naskar

Parameter-free Optimal Rates for Nonlinear Semi-Norm Contractions with Applications to Q-Learning

Algorithms for solving nonlinear fixed-point equations---such as average-reward Q-learning and TD-learning---often involve semi-norm contractions. Achieving parameter-free optimal convergence rates for these methods via Polyak–Ruppert averaging has remained elusive, largely due to the non-monotonici