Cargando…

Universal Artificial Intelligence Sequential Decisions Based on Algorithmic Probability /

Decision Theory = Probability + Utility Theory + + Universal Induction = Ockham + Bayes + Turing = = A Unified View of Artificial Intelligence This book presents sequential decision theory from a novel algorithmic information theory perspective. While the former is suited for active agents in known...

Descripción completa

Detalles Bibliográficos
Clasificación:Libro Electrónico
Autor principal: Hutter, Marcus (Autor)
Autor Corporativo: SpringerLink (Online service)
Formato: Electrónico eBook
Idioma:Inglés
Publicado: Berlin, Heidelberg : Springer Berlin Heidelberg : Imprint: Springer, 2005.
Edición:1st ed. 2005.
Colección:Texts in Theoretical Computer Science. An EATCS Series,
Temas:
Acceso en línea:Texto Completo

MARC

LEADER 00000nam a22000005i 4500
001 978-3-540-26877-2
003 DE-He213
005 20220118045730.0
007 cr nn 008mamaa
008 100301s2005 gw | s |||| 0|eng d
020 |a 9783540268772  |9 978-3-540-26877-2 
024 7 |a 10.1007/b138233  |2 doi 
050 4 |a Q334-342 
050 4 |a TA347.A78 
072 7 |a UYQ  |2 bicssc 
072 7 |a COM004000  |2 bisacsh 
072 7 |a UYQ  |2 thema 
082 0 4 |a 006.3  |2 23 
100 1 |a Hutter, Marcus.  |e author.  |4 aut  |4 http://id.loc.gov/vocabulary/relators/aut 
245 1 0 |a Universal Artificial Intelligence  |h [electronic resource] :  |b Sequential Decisions Based on Algorithmic Probability /  |c by Marcus Hutter. 
250 |a 1st ed. 2005. 
264 1 |a Berlin, Heidelberg :  |b Springer Berlin Heidelberg :  |b Imprint: Springer,  |c 2005. 
300 |a XX, 278 p.  |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 Texts in Theoretical Computer Science. An EATCS Series,  |x 1862-4502 
505 0 |a Short Tour Through the Book -- Simplicity & Uncertainty -- Universal Sequence Prediction -- Agents in Known Probabilistics Environments -- The Universal Algorithmic Agent AIXI -- Important Environmental Classes -- Computational Aspects -- Discussion. 
520 |a Decision Theory = Probability + Utility Theory + + Universal Induction = Ockham + Bayes + Turing = = A Unified View of Artificial Intelligence This book presents sequential decision theory from a novel algorithmic information theory perspective. While the former is suited for active agents in known environments, the latter is suited for passive prediction in unknown environments. The book introduces these two well-known but very different ideas and removes the limitations by unifying them to one parameter-free theory of an optimal reinforcement learning agent embedded in an arbitrary unknown environment. Most if not all AI problems can easily be formulated within this theory, which reduces 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 to AI. 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. 
650 0 |a Artificial intelligence. 
650 0 |a Coding theory. 
650 0 |a Information theory. 
650 0 |a Computer science. 
650 0 |a Machine theory. 
650 0 |a Computer science-Mathematics. 
650 0 |a Mathematical statistics. 
650 1 4 |a Artificial Intelligence. 
650 2 4 |a Coding and Information Theory. 
650 2 4 |a Theory of Computation. 
650 2 4 |a Formal Languages and Automata Theory. 
650 2 4 |a Probability and Statistics in Computer Science. 
710 2 |a SpringerLink (Online service) 
773 0 |t Springer Nature eBook 
776 0 8 |i Printed edition:  |z 9783642060526 
776 0 8 |i Printed edition:  |z 9783540802075 
776 0 8 |i Printed edition:  |z 9783540221395 
830 0 |a Texts in Theoretical Computer Science. An EATCS Series,  |x 1862-4502 
856 4 0 |u https://doi.uam.elogim.com/10.1007/b138233  |z Texto Completo 
912 |a ZDB-2-SCS 
912 |a ZDB-2-SXCS 
950 |a Computer Science (SpringerNature-11645) 
950 |a Computer Science (R0) (SpringerNature-43710)