Nicolas Gast, Bruno Gaujal, Kimang Khun. What is an Optimal Policy in Time-Average MDP?. SIGMETRICS Performance Evaluation Review, 51(2):30-32, September 2023. [doi]
@article{GastGK23-0,
title = {What is an Optimal Policy in Time-Average MDP?},
author = {Nicolas Gast and Bruno Gaujal and Kimang Khun},
year = {2023},
month = {September},
doi = {10.1145/3626570.3626582},
url = {https://doi.org/10.1145/3626570.3626582},
researchr = {https://researchr.org/publication/GastGK23-0},
cites = {0},
citedby = {0},
journal = {SIGMETRICS Performance Evaluation Review},
volume = {51},
number = {2},
pages = {30-32},
}