Playing is believing: the role of beliefs in multi-agent learning

Please use this identifier to cite or link to this item: http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/3688

Full metadata record

DC Field	Value	Language
dc.creator	Chang, Yu-Han	-
dc.creator	Kaelbling, Leslie P.	-
dc.date	2003-11-17T16:46:08Z	-
dc.date	2003-11-17T16:46:08Z	-
dc.date	2003-01	-
dc.date.accessioned	2013-10-09T02:31:57Z	-
dc.date.available	2013-10-09T02:31:57Z	-
dc.date.issued	2013-10-09	-
dc.identifier	http://hdl.handle.net/1721.1/3688	-
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721	-
dc.description	We propose a new classification for multi-agent learning algorithms, with each league of players characterized by both their possible strategies and possible beliefs. Using this classification, we review the optimality of existing algorithms and discuss some insights that can be gained. We propose an incremental improvement to the existing algorithms that seems to achieve average payoffs that are at least the Nash equilibrium payoffs in the long-run against fair opponents.	-
dc.description	Singapore-MIT Alliance (SMA)	-
dc.format	114175 bytes	-
dc.format	application/pdf	-
dc.language	en_US	-
dc.relation	Computer Science (CS);	-
dc.subject	multi-agent learning algorithm	-
dc.subject	repeated games	-
dc.subject	belief	-
dc.subject	game theory	-
dc.subject	Matrix games	-
dc.subject	Nash equilibrium	-
dc.subject	Stochastic games	-
dc.subject	Reinforcement learning	-
dc.subject	PHC-Exploiter	-
dc.title	Playing is believing: the role of beliefs in multi-agent learning	-
dc.type	Article	-
Appears in Collections:	MIT Items

Files in This Item:

There are no files associated with this item.

DSpace JSPUI