|
|
|
|
LEADER |
02830nmm a2200397 u 4500 |
001 |
EB000373174 |
003 |
EBX01000000000000000226226 |
005 |
00000000000000.0 |
007 |
cr||||||||||||||||||||| |
008 |
130626 ||| eng |
020 |
|
|
|a 9783540268772
|
100 |
1 |
|
|a Hutter, Marcus
|
245 |
0 |
0 |
|a Universal Artificial Intelligence
|h Elektronische Ressource
|b Sequential Decisions Based on Algorithmic Probability
|c by Marcus Hutter
|
250 |
|
|
|a 1st ed. 2005
|
260 |
|
|
|a Berlin, Heidelberg
|b Springer Berlin Heidelberg
|c 2005, 2005
|
300 |
|
|
|a XX, 278 p
|b online resource
|
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
|
653 |
|
|
|a Mathematical statistics
|
653 |
|
|
|a Coding and Information Theory
|
653 |
|
|
|a Coding theory
|
653 |
|
|
|a Computer science
|
653 |
|
|
|a Computer science / Mathematics
|
653 |
|
|
|a Probability and Statistics in Computer Science
|
653 |
|
|
|a Artificial Intelligence
|
653 |
|
|
|a Formal Languages and Automata Theory
|
653 |
|
|
|a Machine theory
|
653 |
|
|
|a Information theory
|
653 |
|
|
|a Artificial intelligence
|
653 |
|
|
|a Theory of Computation
|
041 |
0 |
7 |
|a eng
|2 ISO 639-2
|
989 |
|
|
|b Springer
|a Springer eBooks 2005-
|
490 |
0 |
|
|a Texts in Theoretical Computer Science. An EATCS Series
|
028 |
5 |
0 |
|a 10.1007/b138233
|
856 |
4 |
0 |
|u https://doi.org/10.1007/b138233?nosfx=y
|x Verlag
|3 Volltext
|
082 |
0 |
|
|a 006.3
|
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.
|