Normale Ansicht MARC ISBD

Universal artificial intelligence sequential decisions based on algorithmic probability Marcus Hutter

Von:

Hutter, Marcus [aut]

Materialtyp: Text

TextVerlagsnummer: 11012139Sprache: Englisch Reihen: Texts in theoretical computer scienceVerlag: Berlin Heidelberg [u.a.] Springer 2005Beschreibung: XX, 278 S Ill 24 cmInhaltstyp:

Text

Medientyp:

ohne Hilfsmittel zu benutzen

Datenträgertyp:

Band

ISBN:

3540221395
9783540221395

Schlagwörter: Andere physische Formen: Online-Ausg.: Universal Artificial IntellegenceLOC-Klassifikation:

Q335

Andere Klassifikation:

ST 134
ST 300
*68T01
68-01
68T05
68Q30
54.72

Online-Ressourcen:

Bearbeitungsvermerk:

Archivierung/Langzeitarchivierung gewährleistet PEBW

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 AIAndere Ausgaben: Online-Ausg.: / Universal Artificial Intellegence

Exemplare ( 1 )
Titelinformationen ( 4 )

Exemplare
Medientyp	Aktuelle Bibliothek	Sammlung	Standort	Signatur	Status	Fälligkeitsdatum	Barcode
Buch	Gebäude E2 3 (UdS Campusbibliothek für Informatik und Mathematik)	Campusbibliothek für Informatik und Mathematik (E2 3)	Books A-Z (1st)	HUT m 2005:1 1.Ex (Regal durchstöbern(Öffnet sich unterhalb))	Verfügbar		2000000227061

Literaturverz. S. [251] - 263

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 AI

Universal Artificial Intellegence

Archivierung/Langzeitarchivierung gewährleistet PEBW pdager DE-31