@article{globalconvergenceofaveragerewardconstrai,
  title = {Global Convergence of Average Reward Constrained MDPs with Neural Critic and General Policy Parameterization},
  author = {Anirudh Satheesh and Pankaj Kumar Barman and Washim Uddin Mondal and Vaneet Aggarwal},
  year = {2026},
  eprint = {2603.07698},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.07698},
}