Gabriel Dulac-Arnold, Ludovic Denoyer, Philippe Preux, Patrick Gallinari. Fast Reinforcement Learning with Large Action Sets Using Error-Correcting Output Codes for MDP Factorization. In Peter A. Flach, Tijl De Bie, Nello Cristianini, editors, Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2012, Bristol, UK, September 24-28, 2012. Proceedings, Part II. Volume 7524 of Lecture Notes in Computer Science, pages 180-194, Springer, 2012. [doi]
@inproceedings{Dulac-ArnoldDPG12,
title = {Fast Reinforcement Learning with Large Action Sets Using Error-Correcting Output Codes for MDP Factorization},
author = {Gabriel Dulac-Arnold and Ludovic Denoyer and Philippe Preux and Patrick Gallinari},
year = {2012},
doi = {10.1007/978-3-642-33486-3_12},
url = {http://dx.doi.org/10.1007/978-3-642-33486-3_12},
researchr = {https://researchr.org/publication/Dulac-ArnoldDPG12},
cites = {0},
citedby = {0},
pages = {180-194},
booktitle = {Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2012, Bristol, UK, September 24-28, 2012. Proceedings, Part II},
editor = {Peter A. Flach and Tijl De Bie and Nello Cristianini},
volume = {7524},
series = {Lecture Notes in Computer Science},
publisher = {Springer},
isbn = {978-3-642-33485-6},
}