Saba Q. Yahyaa, Madalina M. Drugan, Bernard Manderick. Annealing-pareto multi-objective multi-armed bandit algorithm. In 2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2014, Orlando, FL, USA, December 9-12, 2014. pages 1-8, IEEE, 2014. [doi]
@inproceedings{YahyaaDM14-2,
title = {Annealing-pareto multi-objective multi-armed bandit algorithm},
author = {Saba Q. Yahyaa and Madalina M. Drugan and Bernard Manderick},
year = {2014},
doi = {10.1109/ADPRL.2014.7010619},
url = {http://dx.doi.org/10.1109/ADPRL.2014.7010619},
researchr = {https://researchr.org/publication/YahyaaDM14-2},
cites = {0},
citedby = {0},
pages = {1-8},
booktitle = {2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2014, Orlando, FL, USA, December 9-12, 2014},
publisher = {IEEE},
isbn = {978-1-4799-4553-5},
}