Odalric-Ambrym Maillard, Phuong Nguyen, Ronald Ortner, Daniil Ryabko
Optimal Regret Bounds for Selecting the State Representation in Reinforcement Learning
ICML, 2013.
@inproceedings{ICML-c1-2013-MaillardNOR, author = "Odalric-Ambrym Maillard and Phuong Nguyen and Ronald Ortner and Daniil Ryabko", booktitle = "{Proceedings of the 30th International Conference on Machine Learning, Cycle 1}", ee = "http://jmlr.org/proceedings/papers/v28/maillard13.html", pages = "543--551", publisher = "{JMLR.org}", series = "{JMLR Proceedings}", title = "{Optimal Regret Bounds for Selecting the State Representation in Reinforcement Learning}", volume = 28, year = 2013, }