國立高雄大學圖資館 |

Language: English

Back

Making friends on the flyadvances in...

Barrett, Samuel.

Making friends on the flyadvances in ad hoc teamwork /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Making friends on the flyby Samuel Barrett.
Reminder of title:	advances in ad hoc teamwork /
Author:	Barrett, Samuel.
Published:	Cham :Springer International Publishing :2015.
Description:	xx, 144 p. :ill. (some col.), digital ;24 cm.
Contained By:	Springer eBooks
Subject:	Ad hoc networks (Computer networks)
Online resource:	http://dx.doi.org/10.1007/978-3-319-18069-4
ISBN:	9783319180694 (electronic bk.)

Making friends on the flyadvances in ad hoc teamwork /
Barrett, Samuel.

Making friends on the flyadvances in ad hoc teamwork /[electronic resource] :by Samuel Barrett. - Cham :Springer International Publishing :2015. - xx, 144 p. :ill. (some col.), digital ;24 cm. - Studies in computational intelligence,v.6031860-949X ;. - Studies in computational intelligence ;v. 216..

Introduction -- Problem Description -- Background -- Related Work -- The PLASTIC Algorithms -- Theoretical Analysis of PLASTIC -- Empirical Evaluation -- Discussion and Conclusion.

This book is devoted to the encounter and interaction of agents such as robots with other agents and describes how they cooperate with their previously unknown teammates, forming an Ad Hoc team. It presents a new algorithm, PLASTIC, that allows agents to quickly adapt to new teammates by reusing knowledge learned from previous teammates. PLASTIC is instantiated in both a model-based approach, PLASTIC-Model, and a policy-based approach, PLASTIC-Policy. In addition to reusing knowledge learned from previous teammates, PLASTIC also allows users to provide expert-knowledge and can use transfer learning (such as the new TwoStageTransfer algorithm) to quickly create models of new teammates when it has some information about its new teammates. The effectiveness of the algorithm is demonstrated on three domains, ranging from multi-armed bandits to simulated robot soccer games.

ISBN: 9783319180694 (electronic bk.)

Standard No.: 10.1007/978-3-319-18069-4doiSubjects--Topical Terms:

309678
Ad hoc networks (Computer networks)

LC Class. No.: TK5105.77

Dewey Class. No.: 004.6

Making friends on the flyadvances in ad hoc teamwork /
LDR:02071nmm a2200325 a 4500 001 469051
003 DE-He213
005 20151229094116.0
006 m d
007 cr nn 008maaau
008 160118s2015 gw s 0 eng d
020 $a 9783319180694 (electronic bk.)
020 $a 9783319180687 (paper)
024 7 $a 10.1007/978-3-319-18069-4 $2 doi
035 $a 978-3-319-18069-4
040 $a GP $c GP
041 0 $a eng
050 4 $a TK5105.77
072 7 $a UYQ $2 bicssc
072 7 $a COM004000 $2 bisacsh
082 0 4 $a 004.6 $2 23
090 $a TK5105.77 $b .B274 2015
100 1 $a Barrett, Samuel. $3 724880
245 1 0 $a Making friends on the fly $h [electronic resource] : $b advances in ad hoc teamwork / $c by Samuel Barrett.
260 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2015.
300 $a xx, 144 p. : $b ill. (some col.), digital ; $c 24 cm.
490 1 $a Studies in computational intelligence, $x 1860-949X ; $v v.603
505 0 $a Introduction -- Problem Description -- Background -- Related Work -- The PLASTIC Algorithms -- Theoretical Analysis of PLASTIC -- Empirical Evaluation -- Discussion and Conclusion.
520 $a This book is devoted to the encounter and interaction of agents such as robots with other agents and describes how they cooperate with their previously unknown teammates, forming an Ad Hoc team. It presents a new algorithm, PLASTIC, that allows agents to quickly adapt to new teammates by reusing knowledge learned from previous teammates. PLASTIC is instantiated in both a model-based approach, PLASTIC-Model, and a policy-based approach, PLASTIC-Policy. In addition to reusing knowledge learned from previous teammates, PLASTIC also allows users to provide expert-knowledge and can use transfer learning (such as the new TwoStageTransfer algorithm) to quickly create models of new teammates when it has some information about its new teammates. The effectiveness of the algorithm is demonstrated on three domains, ranging from multi-armed bandits to simulated robot soccer games.
650 0 $a Ad hoc networks (Computer networks) $3 309678
650 0 $a Multiagent systems. $3 484868
650 1 4 $a Engineering. $3 210888
650 2 4 $a Computational Intelligence. $3 338479
650 2 4 $a Game Theory, Economics, Social and Behav. Sciences. $3 274083
650 2 4 $a Socio- and Econophysics, Population and Evolutionary Models. $3 495595
650 2 4 $a Robotics and Automation. $3 357111
650 2 4 $a Artificial Intelligence (incl. Robotics) $3 252959
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer eBooks
830 0 $a Studies in computational intelligence ; $v v. 216. $3 380871
856 4 0 $u http://dx.doi.org/10.1007/978-3-319-18069-4
950 $a Engineering (Springer-11647)