Takeshi Shibuya, Seiji Yasunobu. Reinforcement learning with nonstationary reward depending on the episode. In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, Anchorage, Alaska, USA, October 9-12, 2011. pages 2145-2150, IEEE, 2011. [doi]
@inproceedings{ShibuyaY11,
title = {Reinforcement learning with nonstationary reward depending on the episode},
author = {Takeshi Shibuya and Seiji Yasunobu},
year = {2011},
doi = {10.1109/ICSMC.2011.6083989},
url = {http://dx.doi.org/10.1109/ICSMC.2011.6083989},
researchr = {https://researchr.org/publication/ShibuyaY11},
cites = {0},
citedby = {0},
pages = {2145-2150},
booktitle = {Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, Anchorage, Alaska, USA, October 9-12, 2011},
publisher = {IEEE},
isbn = {978-1-4577-0652-3},
}