Skip navigation
Skip navigation

On the computability of AIXI

Leike, Jan; Hutter, Marcus

Description

How could we solve the machine learning and the artificial intelligence problem if we had infinite computation? Solomonoff induction and the reinforcement learning agent AIXI are proposed answers to this question. Both are known to be incomputable. In this paper, we quantify this using the arithmetical hierarchy, and prove upper and corresponding lower bounds for incomputability. We show that AIXI is not limit computable, thus it cannot be approximated using finite computation. Our main result...[Show more]

CollectionsANU Research Publications
Date published: 2015
Type: Conference paper
URI: http://hdl.handle.net/1885/103302
Source: Uncertainty in Artificial Intelligence - Proceedings of the 31st Conference, UAI 2015

Download

File Description SizeFormat Image
01_Leike_On_the_computability_of_AIXI_2015.pdf4.85 MBAdobe PDF    Request a copy


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

Updated:  23 August 2018/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator