Skip navigation
Skip navigation

Universal sequential decisions in unknown environments

Hutter, Marcus

Description

We give a brief introduction to the AIXI model, which unifies and overcomes the limitations of sequential decision theory and universal Solomonoff induction. While the former theory is suited for active agents in known environments, the latter is suited for passive prediction of unknown environments.

dc.contributor.authorHutter, Marcus
dc.date.accessioned2015-09-04T00:05:42Z
dc.date.available2015-09-04T00:05:42Z
dc.identifier.isbn90-393-2874-9
dc.identifier.issn1389-5184
dc.identifier.urihttp://hdl.handle.net/1885/15169
dc.description.abstractWe give a brief introduction to the AIXI model, which unifies and overcomes the limitations of sequential decision theory and universal Solomonoff induction. While the former theory is suited for active agents in known environments, the latter is suited for passive prediction of unknown environments.
dc.publisherUtrecht University
dc.relation.ispartofProceedings of the fifth European Workshop on Reinforcement Learning (EWRL-5)
dc.rights© The Author(s)
dc.subjectArtificial intelligence
dc.subjectRational agents
dc.subjectsequential decision theory
dc.subjectuniversal Solomonoff induction
dc.subjectalgorithmic probability
dc.titleUniversal sequential decisions in unknown environments
dc.typeConference paper
dc.date.issued2001
local.type.statusPublished Version
local.contributor.affiliationHutter, M., Research School of Computer Science, The Australian National University
local.bibliographicCitation.startpage25
local.bibliographicCitation.lastpage26
CollectionsANU Research Publications

Download

There are no files associated with this item.


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

Updated:  19 May 2020/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator