Skip navigation
Skip navigation

Universal artificial intelligence: sequential decisions based on algorithmic probability

Hutter, Marcus

Description

This book presents sequential decision theory from a novel algorithmic information theory perspective. While the former theory is suited for active agents in known environments, the latter is suited for passive prediction of unknown environments. The book introduces these two well-known but very different ideas and removes the limitations by unifying them to one parameter-free ...[Show more]

dc.contributor.authorHutter, Marcus
dc.date.accessioned2015-09-01T05:39:09Z
dc.date.available2015-09-01T05:39:09Z
dc.identifier.isbn3-540-22139-5
dc.identifier.urihttp://hdl.handle.net/1885/15055
dc.description.abstractThis book presents sequential decision theory from a novel algorithmic information theory perspective. While the former theory is suited for active agents in known environments, the latter is suited for passive prediction of 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 interacting with an arbitrary unknown world. 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. Formal definitions of intelligence order relations, the horizon problem and relations to other approaches to AI are discussed. 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.
dc.description.sponsorshipSNF grant 2000-61847.
dc.publisherSpringer Verlag
dc.rights© Springer-Verlag Berlin Heidelberg 2005.
dc.subjectArtificial intelligence
dc.subjectalgorithmic probability
dc.subjectsequential decision theory
dc.subjectSolomonoff induction
dc.subjectKolmogorov complexity
dc.subjectBayes mixture distributions
dc.subjectreinforcement learning
dc.subjectuniversal sequence prediction
dc.subjecttight loss and error bounds
dc.subjectLevin search
dc.subjectstrategic games
dc.subjectfunction minimization
dc.subjectsupervised learning
dc.titleUniversal artificial intelligence: sequential decisions based on algorithmic probability
dc.typeBook
dc.date.issued2005
local.type.statusMetadata only
local.contributor.affiliationHutter, M., Research School of Computer Science, The Australian National University
local.bibliographicCitation.startpage1
local.bibliographicCitation.lastpage280
local.identifier.doi10.1007/b138233
CollectionsANU Research Publications

Download

There are no files associated with this item.


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  19 May 2020/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator