Ronald Ortner. Pseudometrics for State Aggregation in Average Reward Markov Decision Processes. In Marcus Hutter, Rocco A. Servedio, Eiji Takimoto, editors, Algorithmic Learning Theory, 18th International Conference, ALT 2007, Sendai, Japan, October 1-4, 2007, Proceedings. Volume 4754 of Lecture Notes in Computer Science, pages 373-387, Springer, 2007. [doi]
@inproceedings{Ortner07:0,
title = {Pseudometrics for State Aggregation in Average Reward Markov Decision Processes},
author = {Ronald Ortner},
year = {2007},
doi = {10.1007/978-3-540-75225-7_30},
url = {http://dx.doi.org/10.1007/978-3-540-75225-7_30},
tags = {Markov},
researchr = {https://researchr.org/publication/Ortner07%3A0},
cites = {0},
citedby = {0},
pages = {373-387},
booktitle = {Algorithmic Learning Theory, 18th International Conference, ALT 2007, Sendai, Japan, October 1-4, 2007, Proceedings},
editor = {Marcus Hutter and Rocco A. Servedio and Eiji Takimoto},
volume = {4754},
series = {Lecture Notes in Computer Science},
publisher = {Springer},
isbn = {978-3-540-75224-0},
}