@inproceedings{8b7b0e61f7b8490499914548f6c1ae17,
title = "Using localization and factorization to reduce the complexity of reinforcement learning",
abstract = "General reinforcement learning is a powerful framework for artificial intelligence that has seen much theoretical progress since introduced fifteen years ago.We have previously provided guarantees for cases with finitely many possible environments. Though the results are the best possible in general, a linear dependence on the size of the hypothesis class renders them impractical. However, we dramatically improved on these by introducing the concept of environments generated by combining laws. The bounds are then linear in the number of laws needed to generate the environment class. This number is identified as a natural complexity measure for classes of environments. The individual law might only predict some feature (factorization) and only in some contexts (localization). We here extend previous deterministic results to the important stochastic setting.",
keywords = "Bounds, Laws, Optimism, Reinforcement learning",
author = "Peter Sunehag and Marcus Hutter",
note = "Publisher Copyright: {\textcopyright} Springer International Publishing Switzerland 2015.; 8th International Conference on Artificial General Intelligence, AGI 2015 ; Conference date: 22-07-2015 Through 25-07-2015",
year = "2015",
doi = "10.1007/978-3-319-21365-1_19",
language = "English",
isbn = "9783319213644",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "177--186",
editor = "Alexey Potapov and Jordi Bieger and Ben Goertzel",
booktitle = "Artificial General Intelligence - 8th International Conference, AGI 2015, Proceedings",
address = "Germany",
}