Output details
11 - Computer Science and Informatics
University College London
Return to search
Output 0 of 0 in the submission
Article title
A Monte-Carlo AIXI Approximation
Type
D - Journal article
DOI
-
Title of journal
Journal Artificial Intelligence Research (JAIR)
Article number
-
Volume number
40
Issue number
11
First page of article
95-142
ISSN of journal
1943-5037
Year of publication
2011
URL
-
Number of additional authors
4
Additional information
<12>This was the first paper to achieve a practical and high-performance approximation to a universally optimal agent. It builds on Hutter's AIXI: a universal, optimal agent for artificial intelligence - which is, unfortunately, incomputable. The agent developed in this paper is both formally proven to converge to universally optimal decisions (within a restricted class of k-Markov environments); was empirically shown to outperform previous approaches; and was validated on significantly harder problems than previous approaches. Our AIXI approximation is now used commercially by DeepMind Technologies to build general-purpose agents in various domains. Journal version of the 2010 AAAI conference paper.
Interdisciplinary
-
Cross-referral requested
-
Research group
None
Citation count
9
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-
