Lukasz Szpruch

collaborators

3 papers

math.OC2026

Convergence of an actor-critic gradient flow for entropy regularised MDPs in general spaces

Denis Zorba, David Å iÅ¡ka, Lukasz Szpruch

We prove the stability and global convergence of a coupled actor-critic gradient flow for infinite-horizon and entropy-regularised Markov decision processes (MDPs) in continuous st…

cs.LG2026

Global linear convergence of entropy-regularized softmax policy gradient beyond tabular MDPs

Ziyue Chen, David Å iÅ¡ka, Lukasz Szpruch

We study the global convergence of policy gradient for infinite-horizon entropy-regularized Markov decision processes (MDPs) with continuous state and action spaces. We consider lo…

math.OC2026

Mirror descent actor-critic methods for entropy regularised MDPs in general spaces: stability and convergence

Denis Zorba, David Å iÅ¡ka, Lukasz Szpruch

We provide theoretical guarantees for convergence of discrete-time policy mirror descent with inexact advantage functions updated using temporal difference (TD) learning for entrop…