Universal artificial intelligence : sequential decisions based on algorithmic probability / Marcus Hutter

Von:

Hutter, Marcus, 1967- [aut]

Resource type: Ressourcentyp: BuchBuchVerlagsnummer: 11012139Sprache: Englisch Reihen: Texts in theoretical computer scienceVerlag: Berlin ; Heidelberg [u.a.] : Springer, 2005Beschreibung: XX, 278 S : Ill ; 24 cmISBN:

3540221395
9783540221395

Schlagwörter:

Andere physische Formen: Erscheint auch als: Universal Artificial Intellegence. Online-Ausgabe. Berlin, Heidelberg : Springer-Verlag Berlin Heidelberg, 2005. Online-Ressource (XX, 278 p, digital)DDC-Klassifikation:

006.31
004
006.3'1
004 510
004

MSC: MSC: *68T01 | 68-01 | 68T05 | 68Q30RVK: RVK: ST 134 | ST 300 | ST 302LOC-Klassifikation:

Q335

Zusammenfassung: This book presents sequential decision theory from a novel algorithmic information theory perspective. While the former is suited for active agents in known environment, the latter is suited for passive prediction in unknown environment. The book introduces these two different ideas and removes the limitations by unifying them to one parameter-free theory of an optimal reinforcement learning agent embedded in an unknown environment. Most AI problems can easily be formulated within this theory, reducing the conceptual problems to pure computational ones. Considered problem classes include sequence prediction, strategic games, function minimization, reinforcement and supervised learning. The discussion includes formal definitions of intelligence order relations, the horizon problem and relations to other approaches. One intention of this book is to excite a broader AI audience about abstract algorithmic information theory concepts, and conversely to inform theorists about exciting applications to AICall number: Grundsignatur: 2004 A 28093PPN: PPN: 390675083

Exemplare ( 1 )

Exemplare
Medientyp	Heimatbibliothek	Sammlung	Standort	Signatur	Status	Barcode
Freihandbestand ausleihbar	Bibliothek Campus Süd	inf 6.20	Lesesaal Wirtschaftswissenschaften und Informatik (LSW)	2004 A 28093	Verfügbar	47051235090

Anzahl Vormerkungen: 0