Tixian Wang, Amirhossein Taghvaei, Prashant G. Mehta. Q-learning for POMDP: An application to learning locomotion gaits. In 58th IEEE Conference on Decision and Control, CDC 2019, Nice, France, December 11-13, 2019. pages 2758-2763, IEEE, 2019. [doi]
@inproceedings{WangTM19,
title = {Q-learning for POMDP: An application to learning locomotion gaits},
author = {Tixian Wang and Amirhossein Taghvaei and Prashant G. Mehta},
year = {2019},
doi = {10.1109/CDC40024.2019.9030143},
url = {https://doi.org/10.1109/CDC40024.2019.9030143},
researchr = {https://researchr.org/publication/WangTM19},
cites = {0},
citedby = {0},
pages = {2758-2763},
booktitle = {58th IEEE Conference on Decision and Control, CDC 2019, Nice, France, December 11-13, 2019},
publisher = {IEEE},
}