Dejan V. Djonin, Vikram Krishnamurthy. Q-Learning Algorithms for Constrained Markov Decision Processes With Randomized Monotone Policies: Application to MIMO Transmission Control. IEEE Transactions on Signal Processing, 55(5-2):2170-2181, 2007. [doi]
@article{DjoninK07,
title = {Q-Learning Algorithms for Constrained Markov Decision Processes With Randomized Monotone Policies: Application to MIMO Transmission Control},
author = {Dejan V. Djonin and Vikram Krishnamurthy},
year = {2007},
doi = {10.1109/TSP.2007.893228},
url = {http://doi.ieeecomputersociety.org/10.1109/TSP.2007.893228},
tags = {Markov},
researchr = {https://researchr.org/publication/DjoninK07},
cites = {0},
citedby = {0},
journal = {IEEE Transactions on Signal Processing},
volume = {55},
number = {5-2},
pages = {2170-2181},
}