Sumit Kunnumkal, Huseyin Topaloglu. Exploiting the Structural Properties of the Underlying Markov Decision Problem in the Q-Learning Algorithm. INFORMS Journal on Computing, 20(2):288-301, 2008. [doi]
@article{KunnumkalT08,
title = {Exploiting the Structural Properties of the Underlying Markov Decision Problem in the Q-Learning Algorithm},
author = {Sumit Kunnumkal and Huseyin Topaloglu},
year = {2008},
doi = {10.1287/ijoc.1070.0240},
url = {http://dx.doi.org/10.1287/ijoc.1070.0240},
tags = {Markov},
researchr = {https://researchr.org/publication/KunnumkalT08},
cites = {0},
citedby = {0},
journal = {INFORMS Journal on Computing},
volume = {20},
number = {2},
pages = {288-301},
}