Proceedings of the 3d Conference on Artificial General Intelligence (2010)

Frontier Search

Authors
Yi Sun, Tobias Glasmachers, Tom Schaul, Jürgen Schmidhuber
Corresponding Author
Yi Sun
Available Online June 2010.
DOI
10.2991/agi.2010.25How to use a DOI?
Abstract

How to search the space of programs for a code that solves a given problem? Standard asymptotically optimal Universal Search orders programs by Levin complexity, implementing an exponential trade-off between program length and runtime. Depending on the problem, however, sometimes we may have a good reason to greatly favor short programs over fast ones, or vice versa. Frontier Search is a novel framework applicable to a wide class of such trade-offs between program size and runtime, and in many ways more general than previous work. We analyze it in depth and derive exact conditions for its applicability.

Copyright
© 2010, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

Volume Title
Proceedings of the 3d Conference on Artificial General Intelligence (2010)
Series
Advances in Intelligent Systems Research
Publication Date
June 2010
ISBN
10.2991/agi.2010.25
ISSN
1951-6851
DOI
10.2991/agi.2010.25How to use a DOI?
Copyright
© 2010, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Cite this article

TY  - CONF
AU  - Yi Sun
AU  - Tobias Glasmachers
AU  - Tom Schaul
AU  - Jürgen Schmidhuber
PY  - 2010/06
DA  - 2010/06
TI  - Frontier Search
BT  - Proceedings of the 3d Conference on Artificial General Intelligence (2010)
PB  - Atlantis Press
SP  - 118
EP  - 123
SN  - 1951-6851
UR  - https://doi.org/10.2991/agi.2010.25
DO  - 10.2991/agi.2010.25
ID  - Sun2010/06
ER  -