Mathematical Research Data Initiative
Main page
Recent changes
Random page
Help about MediaWiki
Create a new Item
Create a new Property
Create a new EntitySchema
Merge two items
In other projects
Discussion
View source
View history
Purge
English
Log in

Asymptotic non-learnability of universal agents with computable horizon functions

From MaRDI portal
Publication:1939266
Jump to:navigation, search

DOI10.1016/j.tcs.2012.10.014zbMath1277.68279OpenAlexW2137938746MaRDI QIDQ1939266

Laurent Orseau

Publication date: 4 March 2013

Published in: Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.tcs.2012.10.014


zbMATH Keywords

reinforcement learningAIXIuniversal artificial intelligencesolomonoff induction


Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) General topics in artificial intelligence (68T01) Agent technology and artificial intelligence (68T42)


Related Items (3)

Universal knowledge-seeking agents ⋮ On the computability of Solomonoff induction and AIXI ⋮ On the Computability of Solomonoff Induction and Knowledge-Seeking




This page was built for publication: Asymptotic non-learnability of universal agents with computable horizon functions

Retrieved from "https://portal.mardi4nfdi.de/w/index.php?title=Publication:1939266&oldid=14375691"
Tools
What links here
Related changes
Special pages
Printable version
Permanent link
Page information
MaRDI portal item
This page was last edited on 1 February 2024, at 16:46.
Privacy policy
About MaRDI portal
Disclaimers
Imprint
Powered by MediaWiki