notesum.ai

Published at November 18

Fast Convergence of Softmax Policy Mirror Ascent

cs.AI
cs.RO

Released Date: November 18, 2024

Authors: Reza Asad1, Reza Babanezhad2, Issam Laradji3, Nicolas Le Roux4, Sharan Vaswani1

Aff.: 1Simon Fraser University; 2Samsung AI; 3ServiceNow; 4Mila, Université de Montréal, McGill

Arxiv: http://arxiv.org/abs/2411.12042v1