Tobias Graf, Marco Platzner. Adaptive playouts for online learning of policies during Monte Carlo Tree Search. Theoretical Computer Science, 644:53-62, 2016. [doi]
@article{GrafP16,
title = {Adaptive playouts for online learning of policies during Monte Carlo Tree Search},
author = {Tobias Graf and Marco Platzner},
year = {2016},
doi = {10.1016/j.tcs.2016.06.029},
url = {http://dx.doi.org/10.1016/j.tcs.2016.06.029},
researchr = {https://researchr.org/publication/GrafP16},
cites = {0},
citedby = {0},
journal = {Theoretical Computer Science},
volume = {644},
pages = {53-62},
}