Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability

by Marcus Hutter

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.

Genres: Artificial Intelligence, Computer Science, Textbooks

298 pages, Paperback

First published January 1, 2004

Reviews

[Jovany Agathe · Rating 5 out of 5]

This book differs from most books on the theoretical formulations of artificial intelligence in that it attempts to give a more rigorous accounting of machine learning and to rank machines according to their intelligence. To accomplish this ranking, the author introduces a concept called `universal artificial intelligence,' which is constructed in the context of algorithmic information theory. In fact, the book could be considered to be a formulation of artificial intelligence from the standpoint of algorithmic information theory, and is strongly dependent on such notions as Kolmogorov complexity, the Solomonoff universal prior, Martin-Lof random sequences and Occam's razor. These are all straightforward mathematical concepts with which to work with, the only issue for researchers being their efficacy in giving a useful notion of machine intelligence.

[Kevin Doran · Rating 2 out of 5]

Note: not finished.

Has anyone ever read all of this book? Properly? I'm skeptical.

Anyway, a note to the author/publisher: please increase the line-spacing. The symbols on one line are so close to the next line that you have to double-check which line they are part of.

[Daanish Shabbir]

This is impossible to read (unless u do a phd with Marcus?)! but I know now the basics of AIXI