Optimistic agents are asymptotically optimal

Simple item page
dc.contributor.authorSunehag, Peter
dc.contributor.authorHutter, Marcus
dc.date.accessioned2015-08-17T04:24:06Z
dc.date.available2015-08-17T04:24:06Z
dc.date.issued2012
dc.description.abstractWe use optimism to introduce generic asymptotically optimal reinforcement learning agents. They achieve, with an arbitrary finite or compact class of environments, asymptotically optimal behavior. Furthermore, in the finite deterministic case we provide finite error bounds.en_AU
dc.identifier.isbn978-3-642-35100-6en_AU
dc.identifier.issn0302-9743en_AU
dc.identifier.urihttp://hdl.handle.net/1885/14734
dc.publisherSpringer Verlagen_AU
dc.relationhttp://purl.org/au-research/grants/arc/DP120100950en_AU
dc.relation.ispartofAI 2012: Advances in Artificial Intelligence: 25th Australasian Joint Conference, Sydney, Australia, December 4-7, 2012. Proceedingsen_AU
dc.rights© Springer-Verlag Berlin Heidelberg 2012. 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 17/08/15)en_AU
dc.subjectReinforcement Learningen_AU
dc.subjectOptimismen_AU
dc.subjectOptimalityen_AU
dc.titleOptimistic agents are asymptotically optimalen_AU
dc.typeConference paperen_AU
local.bibliographicCitation.lastpage26en_AU
local.bibliographicCitation.startpage15en_AU
local.contributor.affiliationSunehag, P., 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.authoruidu4753099en_AU
local.identifier.citationvolume7691en_AU
local.identifier.doi10.1007/978-3-642-35101-3_2en_AU
local.type.statusAccepted Versionen_AU

Downloads

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
Sunehag and Hutter Optimistic Agents are Asymptotically Optimal 2012.pdf
Size:
125.76 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