Peter L. Bartlett, Ambuj Tewari. REGAL: A Regularization based Algorithm for Reinforcement Learning in Weakly Communicating MDPs. In Jeff Bilmes, Andrew Y. Ng, editors, UAI 2009, Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence, Montreal, QC, Canada, June 18-21, 2009. pages 35-42, AUAI Press, 2009. [doi]
@inproceedings{BartlettT09,
title = {REGAL: A Regularization based Algorithm for Reinforcement Learning in Weakly Communicating MDPs},
author = {Peter L. Bartlett and Ambuj Tewari},
year = {2009},
url = {http://uai.sis.pitt.edu/displayArticleDetails.jsp?mmnu=1&smnu=2&article_id=1617&proceeding_id=25},
researchr = {https://researchr.org/publication/BartlettT09},
cites = {0},
citedby = {0},
pages = {35-42},
booktitle = {UAI 2009, Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence, Montreal, QC, Canada, June 18-21, 2009},
editor = {Jeff Bilmes and Andrew Y. Ng},
publisher = {AUAI Press},
}