Making Friends on the Fly: Advances in Ad Hoc Teamwork

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 kno...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής
Κύριος συγγραφέας: Barrett, Samuel (Συγγραφέας)
Συγγραφή απο Οργανισμό/Αρχή: SpringerLink (Online service)
Μορφή: Ηλεκτρονική πηγή Ηλ. βιβλίο
Γλώσσα:English
Έκδοση: Cham : Springer International Publishing : Imprint: Springer, 2015.
Σειρά:Studies in Computational Intelligence, 603
Θέματα:
Διαθέσιμο Online:Full Text via HEAL-Link
LEADER 02997nam a22005535i 4500
001 978-3-319-18069-4
003 DE-He213
005 20151106161112.0
007 cr nn 008mamaa
008 150525s2015 gw | s |||| 0|eng d
020 |a 9783319180694  |9 978-3-319-18069-4 
024 7 |a 10.1007/978-3-319-18069-4  |2 doi 
040 |d GrThAP 
050 4 |a Q342 
072 7 |a UYQ  |2 bicssc 
072 7 |a COM004000  |2 bisacsh 
082 0 4 |a 006.3  |2 23 
100 1 |a Barrett, Samuel.  |e author. 
245 1 0 |a Making Friends on the Fly: Advances in Ad Hoc Teamwork  |h [electronic resource] /  |c by Samuel Barrett. 
264 1 |a Cham :  |b Springer International Publishing :  |b Imprint: Springer,  |c 2015. 
300 |a XX, 144 p. 26 illus., 19 illus. in color.  |b online resource. 
336 |a text  |b txt  |2 rdacontent 
337 |a computer  |b c  |2 rdamedia 
338 |a online resource  |b cr  |2 rdacarrier 
347 |a text file  |b PDF  |2 rda 
490 1 |a Studies in Computational Intelligence,  |x 1860-949X ;  |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 Engineering. 
650 0 |a Artificial intelligence. 
650 0 |a Game theory. 
650 0 |a Sociophysics. 
650 0 |a Econophysics. 
650 0 |a Computational intelligence. 
650 0 |a Robotics. 
650 0 |a Automation. 
650 1 4 |a Engineering. 
650 2 4 |a Computational Intelligence. 
650 2 4 |a Game Theory, Economics, Social and Behav. Sciences. 
650 2 4 |a Socio- and Econophysics, Population and Evolutionary Models. 
650 2 4 |a Robotics and Automation. 
650 2 4 |a Artificial Intelligence (incl. Robotics). 
710 2 |a SpringerLink (Online service) 
773 0 |t Springer eBooks 
776 0 8 |i Printed edition:  |z 9783319180687 
830 0 |a Studies in Computational Intelligence,  |x 1860-949X ;  |v 603 
856 4 0 |u http://dx.doi.org/10.1007/978-3-319-18069-4  |z Full Text via HEAL-Link 
912 |a ZDB-2-ENG 
950 |a Engineering (Springer-11647)