Feb. 9, 2024, 5:43 a.m. | Semih Cayci Niao He R. Srikant

cs.LG updates on arXiv.org arxiv.org

Natural policy gradient (NPG) methods with entropy regularization achieve impressive empirical success in reinforcement learning problems with large state-action spaces. However, their convergence properties and the impact of entropy regularization remain elusive in the function approximation regime. In this paper, we establish finite-time convergence analyses of entropy-regularized NPG with linear function approximation under softmax parameterization. In particular, we prove that entropy-regularized NPG with averaging satisfies the \emph{persistence of excitation} condition, and achieves a fast convergence rate of $\tilde{O}(1/T)$ up to …

approximation convergence cs.lg entropy function gradient impact linear math.oc natural paper policy regularization reinforcement reinforcement learning spaces state stat.ml success

Research Scholar (Technical Research)

@ Centre for the Governance of AI | Hybrid; Oxford, UK

HPC Engineer (x/f/m) - DACH

@ Meshcapade GmbH | Remote, Germany

Data Architect

@ Dyson | India - Bengaluru IT Capability Centre

GTM Operation and Marketing Data Analyst

@ DataVisor | Toronto, Ontario, Canada - Remote

Associate - Strategy & Business Intelligence

@ Hitachi | (HE)Office Rotterdam

Senior Executive - Data Analysis

@ Publicis Groupe | Beirut, Lebanon