Skip navigation
Skip navigation

Asymptotically optimal agents

Lattimore, Tor; Hutter, Marcus

Description

Artificial general intelligence aims to create agents capable of learning to solve arbitrary interesting problems. We define two versions of asymptotic optimality and prove that no agent can satisfy the strong version while in some cases, depending on discounting, there does exist a non-computable weak asymptotically optimal agent.

dc.contributor.authorLattimore, Tor
dc.contributor.authorHutter, Marcus
dc.date.accessioned2015-08-20T00:33:51Z
dc.date.available2015-08-20T00:33:51Z
dc.identifier.isbn978-3-642-24411-7
dc.identifier.issn0302-9743
dc.identifier.urihttp://hdl.handle.net/1885/14810
dc.description.abstractArtificial general intelligence aims to create agents capable of learning to solve arbitrary interesting problems. We define two versions of asymptotic optimality and prove that no agent can satisfy the strong version while in some cases, depending on discounting, there does exist a non-computable weak asymptotically optimal agent.
dc.publisherSpringer Verlag
dc.relation.ispartofAlgorithmic learning theory : 22nd international conference, ALT 2011, Espoo, Finland, October 5-7, 2011 : proceedings
dc.rights© Springer-Verlag Berlin Heidelberg 2011. http://www.sherpa.ac.uk/romeo/issn/0302-9743/..."Author's post-print on any open access repository after 12 months after publication" from SHERPA/RoMEO site (as at 20/08/15)
dc.subjectRational agents
dc.subjectsequential decision theory
dc.subjectartificial general intelligence
dc.subjectreinforcement learning
dc.subjectasymptotic optimality
dc.subjectgeneral discounting
dc.titleAsymptotically optimal agents
dc.typeConference paper
local.identifier.citationvolume6925
dc.date.issued2011-10
local.type.statusAccepted Version
local.contributor.affiliationLattimore, T., Research School of Computer Science, The Australian National University
local.contributor.affiliationHutter, M., Research School of Computer Science, The Australian National University
dc.relationhttp://purl.org/au-research/grants/arc/DP0988049
local.bibliographicCitation.startpage368
local.bibliographicCitation.lastpage382
local.identifier.doi10.1007/978-3-642-24412-4_29
CollectionsANU Research Publications

Download

File Description SizeFormat Image
Lattimore and Hutter Asymptotically Optimal Agents 2011.pdf332.7 kBAdobe PDFThumbnail


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