Skip navigation
Skip navigation

Using Localization and Factorization to Reduce the Complexity of Reinforcement Learning

Sunehag, Peter; Hutter, Marcus


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....[Show more]

CollectionsANU Research Publications
Date published: 2015
Type: Journal article
Source: Journal of Artificial General Intelligence
DOI: 10.1007/978-3-319-21365-1_19


File Description SizeFormat Image
01_Sunehag_Using_Localization_and_2015.pdf185.19 kBAdobe PDF    Request a copy

Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  20 July 2017/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator