Peter Marbach, John N. Tsitsiklis. Approximate Gradient Methods in Policy-Space Optimization of Markov Reward Processes. Discrete Event Dynamic Systems, 13(1-2):111-148, 2003. [doi]
@article{MarbachT03,
title = {Approximate Gradient Methods in Policy-Space Optimization of Markov Reward Processes},
author = {Peter Marbach and John N. Tsitsiklis},
year = {2003},
doi = {10.1023/A:1022145020786},
url = {http://dx.doi.org/10.1023/A:1022145020786},
tags = {optimization, Markov},
researchr = {https://researchr.org/publication/MarbachT03},
cites = {0},
citedby = {0},
journal = {Discrete Event Dynamic Systems},
volume = {13},
number = {1-2},
pages = {111-148},
}