Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy
Gradient Methods

v1v2 (latest)

Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods

4 October 2023

Simon Weissmann

ArXiv (abs)PDF HTML

Papers citing "Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods"

5 / 5 papers shown

Title
Simultaneous Best-Response Dynamics in Random Potential Games Galit Ashkenazi-Golan Domenico Mergoni Cecchelli Edward Plumb 71 0 0 15 May 2025
A learning-based approach to stochastic optimal control under reach-avoid constraint Tingting Ni Maryam Kamgarpour 135 0 0 21 Dec 2024
Structure Matters: Dynamic Policy Gradient Sara Klein Xiangyuan Zhang Tamer Basar Simon Weissmann Leif Döring 59 0 0 07 Nov 2024
Almost sure convergence rates of stochastic gradient methods under gradient domination Simon Weissmann Sara Klein Waïss Azizian Leif Döring 93 3 0 22 May 2024
A policy gradient approach for Finite Horizon Constrained Markov Decision Processes Soumyajit Guin S. Bhatnagar 103 8 0 10 Oct 2022