Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability - Texts in Theoretical Computer Science: an Eatcs Series - Marcus Hutter - Livros - Springer-Verlag Berlin and Heidelberg Gm - 9783642060526 - 6 de novembro de 2010

Caso a capa e o título não sejam correspondentes, considere o título como correto

Conte aos seus amigos sobre este item:

Marcus Hutter
Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability - Texts in Theoretical Computer Science: an Eatcs Series Marcus Hutter Softcover Reprint of Hardcover 1st Ed. 2005 edition

Name: Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability - Texts in Theoretical Computer Science: an Eatcs Series
Price: 88.49 EUR
Availability: OutOfStock
Author: Marcus Hutter

Preço

€ 88,49

Item sob encomenda (no estoque do fornecedor)

Data prevista de entrega 10 - 18 de jun

O que dizem nossos clientes:

Top-vurdering på Google Reviews, baseret på tusinder af anmeldelser.

Política de devolução de 14 dias, em conformidade com a lei europeia de proteção do consumidor

Melhor classificação na Trustpilot

Adicione à sua lista de desejos do iMusic

Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability - Texts in Theoretical Computer Science: an Eatcs Series

Marcus Hutter

Softcover Reprint of Hardcover 1st Ed. 2005 edition

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 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.

298 pages, black & white illustrations

Mídia	Livros Paperback Book (Livro de capa flexível e brochura)
Lançado	6 de novembro de 2010
ISBN13	9783642060526
Editoras	Springer-Verlag Berlin and Heidelberg Gm
Páginas	298
Dimensões	155 × 235 × 16 mm · 426 g
Idioma	Inglês