Cultural advice

The Australian National University acknowledges, celebrates and pays our respects to the Ngunnawal and Ngambri people of the Canberra region and to all First Nations Australians on whose traditional lands we meet and work, and whose cultures are among the oldest continuing cultures in human history.

Aboriginal and Torres Strait Islander peoples are advised that ANU Library collections may include images, names, voices, and other representations of deceased persons.

Material in the collection may contain terms, language or views that reflect the period in which the item was created and may be considered inappropriate today.

The sample-complexity of general reinforcement learning

Simple item page
dc.contributor.authorLattimore, Tor
dc.contributor.authorHutter, Marcus
dc.contributor.authorSunehag, Peter
dc.date.accessioned2015-08-14T02:52:19Z
dc.date.available2015-08-14T02:52:19Z
dc.date.issued2013-06
dc.description.abstractWe present a new algorithm for general reinforcement learning where the true environment is known to belong to a finite class of N arbitrary models. The algorithm is shown to be near-optimal for all but O(N log2 N) timesteps with high probability. Infinite classes are also considered where we show that compactness is a key criterion for determining the existence of uniform sample-complexity bounds. A matching lower bound is given for the finite case.en_AU
dc.identifier.issn1532-4435en_AU
dc.identifier.urihttp://hdl.handle.net/1885/14719
dc.publisherJournal of Machine Learning Researchen_AU
dc.relationhttp://purl.org/au-research/grants/arc/DP120100950en_AU
dc.relation.ispartofProceedings of The 30th International Conference on Machine Learningen_AU
dc.rights© 2013 by the author(s).. Author can archive publisher’s version/PDF. http://www.sherpa.ac.uk/romeo/issn/1532-4435/ as at 14/8/15en_AU
dc.rights.licenseCreative Commons Attribution licence
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectreinforcement learningen_AU
dc.subjectsample complexityen_AU
dc.subjectPAC boundsen_AU
dc.titleThe sample-complexity of general reinforcement learningen_AU
dc.typeConference paperen_AU
dcterms.accessRightsOpen Access
local.bibliographicCitation.lastpage36en_AU
local.bibliographicCitation.startpage28en_AU
local.contributor.affiliationLattimore, T., Research School of Computer Science, The Australian National Universityen_AU
local.contributor.affiliationHutter, M., Research School of Computer Science, The Australian National Universityen_AU
local.contributor.affiliationSunehag, P., Research School of Computer Science, The Australian National Universityen_AU
local.contributor.authoruidu4350841en_AU
local.type.statusPublished Versionen_AU

Downloads

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
Lattimore et al The Sample Complexity 2013.pdf
Size:
393.56 KB
Format:
Adobe Portable Document Format
Description:
Download

License bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
884 B
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

ANU Research Publications

DSpace software copyright © 2002-2026 LYRASIS