Investigations of Different Seeding Strategies in a
Genetic Planner
C. Westerberg, and J. Levine. Applications of Evolutionary Computing, volume 2037 of LNCS, page 505--514. Lake Como, Italy, Springer-Verlag, (18 April 2001)
Abstract
Planning is a difficult and fundamental problem of AI.
An alternative solution to traditional planning
techniques is to apply Genetic Programming. As a
program is similar to a plan a Genetic Planner can be
constructed that evolves plans to the plan solution.
One of the stages of the Genetic Programming algorithm
is the initial population seeding stage. We present
five alternatives to simple random selection based on
simple search. We found that some of these strategies
did improve the initial population, and the efficiency
of the Genetic Planner over simple random selection of
actions.
%0 Conference Paper
%1 westerberg:2001:EvoWorks
%A Westerberg, C. Henrik
%A Levine, John
%B Applications of Evolutionary Computing
%C Lake Como, Italy
%D 2001
%E Boers, Egbert J. W.
%E Cagnoni, Stefano
%E Gottlieb, Jens
%E Hart, Emma
%E Lanzi, Pier Luca
%E Raidl, Gunther R.
%E Smith, Robert E.
%E Tijink, Harald
%I Springer-Verlag
%K STRIPS, algorithms, artificial blocks classical crossover, genetic intelligence, linear one plan, planning, point population programming, representation, seeding, world
%P 505--514
%T Investigations of Different Seeding Strategies in a
Genetic Planner
%U http://citeseer.ist.psu.edu/505122.html
%V 2037
%X Planning is a difficult and fundamental problem of AI.
An alternative solution to traditional planning
techniques is to apply Genetic Programming. As a
program is similar to a plan a Genetic Planner can be
constructed that evolves plans to the plan solution.
One of the stages of the Genetic Programming algorithm
is the initial population seeding stage. We present
five alternatives to simple random selection based on
simple search. We found that some of these strategies
did improve the initial population, and the efficiency
of the Genetic Planner over simple random selection of
actions.
%@ 3-540-41920-9
@inproceedings{westerberg:2001:EvoWorks,
abstract = {Planning is a difficult and fundamental problem of AI.
An alternative solution to traditional planning
techniques is to apply Genetic Programming. As a
program is similar to a plan a Genetic Planner can be
constructed that evolves plans to the plan solution.
One of the stages of the Genetic Programming algorithm
is the initial population seeding stage. We present
five alternatives to simple random selection based on
simple search. We found that some of these strategies
did improve the initial population, and the efficiency
of the Genetic Planner over simple random selection of
actions.},
added-at = {2008-06-19T17:35:00.000+0200},
address = {Lake Como, Italy},
author = {Westerberg, C. Henrik and Levine, John},
biburl = {https://www.bibsonomy.org/bibtex/258c9ddd2fc85e491776b36382b4cc8a6/brazovayeye},
booktitle = {Applications of Evolutionary Computing},
editor = {Boers, Egbert J. W. and Cagnoni, Stefano and Gottlieb, Jens and Hart, Emma and Lanzi, Pier Luca and Raidl, Gunther R. and Smith, Robert E. and Tijink, Harald},
interhash = {21f6f9020d19ce4c31d3ab512a5849a1},
intrahash = {58c9ddd2fc85e491776b36382b4cc8a6},
isbn = {3-540-41920-9},
keywords = {STRIPS, algorithms, artificial blocks classical crossover, genetic intelligence, linear one plan, planning, point population programming, representation, seeding, world},
month = {18 April},
notes = {EvoWorkshops2001. Fitness by simulation},
organisation = {EvoNET},
pages = {505--514},
publisher = {Springer-Verlag},
publisher_address = {Berlin},
series = {LNCS},
timestamp = {2008-06-19T17:54:06.000+0200},
title = {Investigations of Different Seeding Strategies in a
Genetic Planner},
url = {http://citeseer.ist.psu.edu/505122.html},
volume = 2037,
year = 2001
}