Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability - Texts in Theoretical Computer Science: an Eatcs Series - Marcus Hutter - Knjige - Springer-Verlag Berlin and Heidelberg Gm - 9783642060526 - 6. novembra 2010
Če se naslovnica in naslov ne ujemata, je naslov pravilen

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

Cena
€ 87,49

Naročeno iz oddaljenega skladišča

Predvidena dobava 17. - 25. jun
Dodaj na svoj seznam želja iMusic

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

Medij Knjige     Paperback Book   (Knjiga z mehkimi platnicami in lepljenim hrbtom)
Izdano 6. novembra 2010
ISBN13 9783642060526
Založniki Springer-Verlag Berlin and Heidelberg Gm
Strani 298
Dimenzije 155 × 235 × 16 mm   ·   426 g
Jezik Angleščina  

Več od Marcus Hutter

Prikaži vse

Mere med samme udgiver