Using the online cross-entropy method to learn relational policies for playing different games

Simple item page
dc.contributor.authorSarjant, Samuel
dc.contributor.authorPfahringer, Bernhard
dc.contributor.authorDriessens, Kurt
dc.contributor.authorSmith, Tony C.
dc.coverage.spatialConference held at Seoul, South Koreaen_NZ
dc.date.accessioned2011-10-21T03:17:41Z
dc.date.available2011-10-21T03:17:41Z
dc.date.issued2011
dc.description.abstractBy defining a video-game environment as a collection of objects, relations, actions and rewards, the relational reinforcement learning algorithm presented in this paper generates and optimises a set of concise, human-readable relational rules for achieving maximal reward. Rule learning is achieved using a combination of incremental specialisation of rules and a modified online cross-entropy method, which dynamically adjusts the rate of learning as the agent progresses. The algorithm is tested on the Ms. Pac-Man and Mario environments, with results indicating the agent learns an effective policy for acting within each environment.en_NZ
dc.format.mimetypeapplication/pdf
dc.identifier.citationSarjant, S., Pfahringer, B., Driessens, K. & Smith, T. (2011). Using the online cross-entropy method to learn relational policies for playing different games. In Proceeding of 2011 IEEE Conference on Computational Intelligence and Games, Seoul, South Korea, 31 August - 3 September (pp. 182-189).en_NZ
dc.identifier.doi10.1109/CIG.2011.6032005en_NZ
dc.identifier.urihttps://hdl.handle.net/10289/5837
dc.language.isoen
dc.publisherIEEEen_NZ
dc.relation.isPartOfProc 2011 IEEE Conference on Computational Intelligence and Gamesen_NZ
dc.relation.urihttp://cilab.sejong.ac.kr/cig2011/?page_id=792en_NZ
dc.rights© 2011 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.en_NZ
dc.sourceCIG 2011en_NZ
dc.subjectcomputer scienceen_NZ
dc.subjectvideo-gameen_NZ
dc.subjectMachine learning
dc.titleUsing the online cross-entropy method to learn relational policies for playing different gamesen_NZ
dc.typeConference Contributionen_NZ
pubs.begin-page182en_NZ
pubs.elements-id21084
pubs.end-page189en_NZ
pubs.finish-date2011-09-03en_NZ
pubs.start-date2011-08-31en_NZ
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Using the online cross-entropy method.pdf
Size:
908.42 KB
Format:
Adobe Portable Document Format
Thumbnail Image
Name: Using the online cross-entropy method.pdf
Size: 908.42 KB
Kind: Adobe PDF
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Name: license.txt
Size: 1.71 KB
Kind: License
Collections
Computing and Mathematical Sciences Papers