Universal Artificial Intelligence

Sequential Decisions Based on Algorithmic Probability

Marcus Hutter - Collection Texts in theoretical computer science - an EATCS series

278 pages, parution le 27/10/2004

Ajouter à une liste

Indisponible

Résumé

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.

Sommaire

Meta Contents
A Short Tour Through the Book
Simplicity & Uncertainty
Universal Sequence Prediction
Agents in Known Probabilistic Environments
The Universal Algorithmic Agent AIXI
Important Environmental Classes
Computational Aspects
Discussion

Voir tout

Replier

Caractéristiques techniques

	PAPIER
Éditeur(s)	Springer
Auteur(s)	Marcus Hutter
Collection	Texts in theoretical computer science - an EATCS series
Parution	27/10/2004
Nb. de pages	278
Format	16 x 24
Couverture	Relié
Poids	636g
Intérieur	Noir et Blanc
EAN13	9783540221395