The Illinois Genetic Algorithms Laboratory (IlliGAL) is pleased to
announce the publication of the following new technical reports.
 
Most IlliGAL technical reports, as well as reprints of other
publications, are available in hardcopy and can be ordered from the
IlliGAL librarian, (see below for ordering information).  The technical
reports in this announcement are also available electronically on our
ftp and WWW servers (see the end of this announcement for ftp and WWW
access instructions). 
 
========================

IlliGAL Report No 2000003


Goldberg, D.E. (ed.) (2000).  

Genetic Algorithms at the University of Illinois 

Abstract not available (this report is a collection of a number of
papers from the course GE485 at the Department of General Engineering,
from the term Fall 1999).

========================

IlliGAL Report No 2000004

OMEGA - Ordering Messy GA : Solving Permutation Problems with the Fast
Messy Genetic Algorithm and Random Keys

Dimitri Knjazew and David E. Goldberg 

Abstract:
This paper presents an ordering messy genetic algorithm (OmeGA) that is
able to solve difficult permutation problems efficiently. It is
essentially a fast messy genetic algorithm (fmGA) using random keys to
represent chromosomes. Experimental results that show the random
key-based simple genetic algorithm (RKGA) being outperformed by its
messy competitor in 32-length ordering deceptive problems are presented. 

========================

IlliGAL Report No 2000005

Introducing a Genetic Generalization Pressure to the Anticipatory
Classifier System 
Part 1: Theoretical Approach 

Martin Butz, David E. Goldberg, and Wolfgang Stolzmann 

Abstract:
The Anticipatory Classifier System is a learning classifier system that
is based on the cognitive mechanism of anticipatory behavioral control.
Besides the common reward learning, the ACS is able to learn latently
(i.e. to learn in an environment without getting any reward) which is
not possible with reinforcement learning techniques. Furthermore, it is
forming a complete internal representation of the environment and thus,
it is able to use cognitive processes such as reasoning and planning.
Latest research showed that there are problems that challenge the
current ACS learning mechanism. It was observed that the ACS is not
generating accurate, maximally general rules reliably (i.e. rules which
are accurate and in the mean time as general as possible), but it is
sometimes generating over-specific rules. This paper shows how a genetic
algorithm can be used to overcome this present pressure of
over-specification in the ACS mechanism with a genetic generalization
pressure. The ACS works then as a hybrid which learns latently, forms a
cognitive map, and evolves accurate, maximally general rules.

========================

IlliGAL Report No 2000006

Introducing a Genetic Generalization Pressure to the Anticipatory
Classifier System 
Part 2: Performance Analysis 

Martin Butz, David E. Goldberg, and Wolfgang Stolzmann 

Abstract:
The Anticipatory Classifier System (ACS) is able to form a complete
internal representation of an environment. Unlike most other classifier
system and reinforcement learning approaches, it is able to learn
latently (i.e. to learn in an environment without getting any reward).
Compared to other systems which are also able to form an internal
representation of the outside world, the advantage of the ACS is that it
is not forming an identical copy of the environment but it is generating
a complete but more general model. After the observation that the model
is not necessarily maximally general a genetic generalization pressure
was introduced to the ACS (Butz:Technical Report 2000005). This paper
focuses on the different mechanisms in the anticipatory learning
process, which resembles the specification pressure, and in the genetic
algorithm, which realizes the genetic generalization pressure. The
capability of generating maximally general rules and evolving a
completely converged population is investigated in detail. Furthermore,
the paper approaches a first comparison with the XCS classifier system
in different mazes and the multiplexer problem. 

========================

IlliGAL Report No 2000007

Bad Codings and the Utility of Well-Designed Genetic Algorithms 

Franz Rothlauf, David Goldberg and Armin Heinzl 

Abstract:
This paper compares the performance of the Bayesian optimisation
algorithm (BOA) to traditional Genetic Algorithms (GAs) such as the
simple GA, or an Evolution Strategy for a real-world telecommunication
problem. Users often notice that GAs perform well for real-world
problems, but when the problem is slightly scaled up or modified, they
sometimes fail unexpectedly. Competent GAs, such as BOA, however promise
to overcome this problem more efficiently, and to behave more robustly
on demanding problems. In this practical case study we use the
pruefernumber encoding as an example of a bad encoding, that causes GAs
difficulty in finding a good solution. The results of the experiments
show that traditional GAs sometimes succeed and sometimes fail for
different parameter settings or modifications of the encoding. The
behaviour could not be predicted. The BOA however is able to perform as
well or better than the best traditional GA, and more importantly does
not fail once in this case study. It seems that the BOA is a step along
the long road towards more robust and competent GAs, that are easier to
use by real practitioners on problems with unknown complexity.  

-------------------------------------------------------------

RETRIEVAL/ORDERING:
 
   The above IlliGAL reports and publications, along with other 
   publications and source code, are available electronically via FTP or 
   WWW, or as hardcopy directly from us:
 
     FTP:    ftp ftp-illigal.ge.uiuc.edu
             login:  anonymous  
             password:  (your email address)
             cd /pub/papers/IlliGALs  (for reports)   or
             cd /pub/papers/Publications (for preprints) or
             cd /pub/src  (for GA and classifier system source code)
             binary
             get 99022.ps.Z                    (for example) 
 
    Please look at the README files for explanations of what the file 
    names mean.  IlliGAL reports are all compressed postscript files.  
 
     WWW:           To access the IlliGAL home page, open
                    http://www-illigal.ge.uiuc.edu/
 
     HARDCOPY:
 
    You can also order hardcopy versions of most IlliGAL publications
    Use the order form in the web or request them directly 
    (by IlliGAL number or title) from the IlliGAL librarian:
 
     Internet:  [log in to unmask]  Phone:  217/333-2346 
                                             Fax:    217/244-5705 
     Surface mail:   IlliGAL Librarian 
                     Department of General Engineering 
                     117 Transportation Building 
                     104 South Mathews Avenue 
                     Urbana, IL 61801-2996       USA  
 
    When ordering hardcopy, please include your surface mail address!  
 
----------------------------------------------
 Martin Pelikan
 Illinois Genetic Algorithms Laboratory
 University of Illinois at Urbana Champaign
 117 Transportation Building 
 104 S. Mathews Avenue, Urbana, IL 61801
 tel: (217) 333-2346, fax: (217) 244-5705
----------------------------------------------


%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%