activity
20162026
most citedExponential Convergence and stability of Howards's Policy Improvement Algorithm for Controlled Diffusions

30 citations · 54 across the 10 of their papers we have counts for

collaborators
Showing 2026 · math.OCShow all

1 paper · 2 filters

math.OC2026

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

Denis Zorba, David Šiška, 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…