@article{
mondal2026lastiterate,
title={Last-Iterate Convergence of General Parameterized Policies in Constrained {MDP}s},
author={Washim Uddin Mondal and Vaneet Aggarwal},
journal={Transactions on Machine Learning Research},
issn={2835-8856},
year={2026},
url={https://openreview.net/forum?id=JedrMCZC6l},
note={}
}