Copy Link
Add to Bookmark
Report
Alife Digest Number 091
Alife Digest, Number 091
Wednesday, December 16th 1992
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
~ Artificial Life Distribution List ~
~ ~
~ All submissions for distribution to: alife@cognet.ucla.edu ~
~ All list subscriber additions, deletions, or administrative details to: ~
~ alife-request@cognet.ucla.edu ~
~ All software, tech reports to Alife depository through ~
~ anonymous ftp at ftp.cognet.ucla.edu in ~ftp/pub/alife (128.97.50.19) ~
~ ~
~ List maintainers: Liane Gabora and Rob Collins ~
~ Artificial Life Research Group, UCLA ~
~ ~
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Today's Topics:
Calendar of Alife-related Events
Tierra Update: V4.0
Educational Discount on GA software
MEDINFO'95: Preliminary Info
IJCAI-93 Workshop on Dynamically Interacting Robots
Call for Papers: Intn'l Conf Biomedical Engineering Rio 94
SAB92 Report, Hugo de Garis (ETL, Japan)
----------------------------------------------------------------------
Date: Wed, 16 Dec 92 14:50:36 -0800
From: liane@CS.UCLA.EDU (Liane Gabora)
Subject: Calendar of Alife-related Events
**********************************************************************
International Conference on System Sciences, Hawaii Jan 5-8, 1993 v74
Symposium on Pattern Formation, Claremont California Feb 12-13, 1993 v90
Biol and Tech of Autonomous Agents, Trento Italy Mar 1-12, 1993 v88
Conf on Neural Networks, San Francisco CA Mar 28-Apr 1, 1993 v79
Conf on Fuzzy Systems, San Francisco CA Mar 28-Apr 1, 1993 v79
AI and Simulation of Behaviour Conf, Birmingham UK Mar 29-Apr 2, 1993 v75
Intnl Conf on Neural Nets and GAs, Innsbruck, Austria Apr 13-16, 1993 v80
BEAM Robot Olympics, Toronto Canada Apr 22-25, 1993 v81
European Conf on ALife, Brussels May 24-26, 1993 v82
Intnl Workshop Neural Networks, Barcelona Spain June 9-11, 1993 v76
Intelligent Systems for Molecular Biology, Washington July 7-9, 1993 v84
Fifth Intnl Conf on GAs, Urbana-Champaign IL July 17-22, 1993 v80
Dynamically Interacting Robots Workshop Late Aug, 1993 v91
Congress on Medical Informatics, Sao Paulo, Brazil Sept 9-14, 1995 v91
(Send announcements of other activities to alife@cognet.ucla.edu)
**********************************************************************
------------------------------
From: ray@life.slhs.udel.edu
Date: Mon, 30 Nov 1992 16:01:50 -0500
Subject: Tierra Update: V4.0
TIERRA UPDATE
V4.0, November 1992:
This message contains:
1) Availability of Tierra V4.0 Source Code
a) by ftp
b) by snail mail on disk
2) Bug Fixes
3) Three New Instruction Sets Implemented
4) New Memory Allocator Installed by Chris Stephenson of IBM
5) Full Memory Protection Implemented
6) Virtual Debugger Enhanced
7) Diversity Tool Enhanced
8) Tierra Display Color Mapping
9) Alive Variable Changed
10) CM5 Port
11) Future Phylogeny
12) Tierra in the News
13) Tierra Publications
14) Mailing Lists
15) What Tierra Is (If you don't know what Tierra is, read this first)
The body of this announcement is not included, to save space. You may
obtain the announcement by anonymous ftp at:
tierra.slhs.udel.edu [128.175.41.34] and
life.slhs.udel.edu [128.175.41.33]
in the directory: doc/
The file is called: announce.40
If you do not have ftp access, write me at: ray@life.slhs.udel.edu
and I will mail you the file.
------------------------------
From: emergent@aol.com
Subject: Educational Discount on GA software
Date: Tue, 01 Dec 92 19:04:38 EST
Emergent Behavior is pleased to announce our new educational discount
program. We are making MicroGA available for a special discount to
professors interested in teaching classes using GAs.
Here is some information about MicroGA.
MicroGA is an object oriented system for solving problems using Genetic
Algorithms. It uses the C++ language to give it both power and flexibility.
In addition, it is surprisingly easy to use.
Included with MicroGA are sample programs which show how genetic algorithms
can be used for resource allocation and to optimize a traveling salesman
problem. A sample MacApp interface is included with the Macintosh version
which implements: multiple documents, printing, and background processing.
The MS Windows version includes a similar program created using Borland's
Object Windows Li
brary.
Also included with MicroGA is the Galapagosx code generation system. This
powerful utility allows users to quickly create complete applications without
writing any C++ code. It also allows programmers to quickly prototype their
advanced applications. All the user needs to do is fill in a dialog box
defining the constraints and variables for the problem. Galapagos then
writes the necessary source files.
MicroGA is also built to be expandable. It allows programmers to add new
genetic representations, crossover schemes, and population types. This makes
it a great tool for research or education.
MicroGA is currently available for Macintosh and IBM PC compatible
computers. The Macintosh version requires a Macintosh II or higher level
machine. It also requires MPW and a C++ compiler. A 68881 math co-processor
is recommended. The PC compatible version requires MS Windows version 3.0 or
higher and Turbo/Borland C++. All source code is included. Compiled
applications can be made using MicroGA and sold without license fee.
Includes:
* Library with Source Code
* Three Sample Programs with Source
* Sample MacApp/OWL Interface with Source
* Galapagos Code Generator
* 95 page manual with tutorial and detailed member by member technical
reference.
* Special graphics objects for displaying results.
MicroGA is normally available for $249, but with our discount program it is
much more affordable to educational institutions.
buy 10 copies at $90 each for a savings of 64% or buy 30 copies at $75 each
for a savings of 70%.
purchase can be made by check, university purchase order, Visa or Mastercard.
Please contact us if you need more information.
Steve Wilson
Emergent Behavior
635 Wellsbury Way
Palo Alto, CA 94306
(41
5)494-6763
fax: (415) 494-0570
emergent@aol.com
------------------------------
Date: Wed, 9 Dec 1992 17:10 GMT-0200
From: SABBATINI@CCVAX.UNICAMP.BR
Subject: MEDINFO'95: Preliminary Info
From: Renato M.E. Sabbatini - SABBATINI@CCVAX.UNICAMP.BR
Date: November 27 1992
Source: NIBNEWS - An Electronic Newsletter on Medical Informatics
PLEASE FORWARD
-------------------------------------------------------------------------
PRELIMINARY INFORMATION
MEDINFO'95
8th WORLD CONGRESS ON MEDICAL INFORMATICS
The 8th World Congress on Medical Informatics (MEDINFO'95) will be held
in Sao Paulo, Brazil, from 9-14 September 1995. Previous MEDINFO Congresses,
which are promoted by the International Association of Medical Informatics
(IMIA), have taken place in Stockholm (1974), Toronto (1977), Tokyo (1980),
Amsterdam (1983), Washington (1986), Beijing and Singapore (1989) and
Geneva (1992). MEDINFO'95 will be hosted by the Brazilian Society of
Health Informatics, founded 1986.
The event will be held at Sao Paulo City's huge Convention Center, with
a total area of 505,000 square meters, and where up to 4,500 participants
can be conveniently assembled. A Technical Exhibition, featuring
the latest software and hardware products, services and literature in
Medical Informatics, will be held in conjunction with MEDINFO'95.
Sao Paulo is the country's biggest city, actually one of the largest urban
concentrations in the world (17 million inhabitants). It's the most important
commercial, industrial, banking, economic and cultural center in Latin
America; a modern city of skyscrapers, universities, sophisticated
shopping malls, theaters and showplaces. Cultural and night life in Sao
Paulo is intense and varied, with international and local attractions.
Three airports serve the city and provide connections and direct flights
to all major foreign capitals. Besides its rich resources, the state of
Sao Paulo is endowed with beautiful mountain ranges, beaches and many
historical townships that are easily reached by modern express highways.
Furthermore, pre- and post-congress tours to Brazil extremely beautiful
and exotic touristic sites will be arranged, such as the Amazon forest,
Pantanal ecological preserve, Rio de Janeiro, Salvador, the Iguazu falls,
etc., at attractive low prices for foreign visitors.
The scientific and technical program will include plenary and semi-plenary
lectures, tutorials, poster and technical sessions, workshops, theater-style
and tabletop demonstrations, meet-the-experts sessions, technical excursions
and free software exchange.
If you want to receive more information about MEDINFO'95, including the
upcoming Call for Papers, please send your name, title and address (with
fax and/or email location) to MED95@SUNCIS.EPM.ANSP.BR (Dr. D. Sigulem)
or to postal address: MEDINFO'95 Secretariat, CIS/EPM, R. Botucatu, 862
Sao Paulo, SP 04023-062, Brazil.
------------------------------
Date: Wed, 9 Dec 1992 22:47:47 -0800
From: Keiji Kanazawa <kanazawa@cs.ubc.ca>
Subject: IJCAI-93 Workshop on Dynamically Interacting Robots
Call for Papers
Dynamically Interacting Robots
IJCAI-93 Workshop
Chambery, France
August 28, 29, or 30, 1993
This one-day workshop brings together researchers interested in the
issues and challenges in controlling multiple interacting robots. Our
goal is to illuminate issues in dynamic situated agency arising from
the interaction of multiple agents. The technology for experimentation
with robot societies is rapidly becoming available; the workshop
provides an opportunity to identify key issues, vocabulary, and
directions for future research.
The focus of the workshop is experimental work. We hope to assess
theories for controlling multiple interacting robots, and to share
experiences in implementing robot societies. The dynamics inherent in
multi-robot domains, coupled with the opportunities for reasoning about
the possible actions of other robots, leads to new theories for control
and planning in multiple robot systems. We welcome perspectives for
controlling robot societies at the individual and group level. The
robot societies may be engaged in cooperative, competitive, or
individual activities, or combinations thereof.
The workshop provides a forum for discussions of the special challenges
involved with the control of a group of robots in real-time, especially
in the context of advances made in distributed AI, theories of situated
activity, robot control, decision theoretic methods, and adaptive
behavior. One of our aims is to identify clearly the issues involved
in robot societies, and how they might distinguish this research
program from distributed AI in general.
* Issues of Interest
Implemented Systems: Descriptions of and lessons from
implemented systems. Which issues arise from the group dynamics as
opposed to implementational concerns?
Languages/Architectures: What kind of languages are needed
for describing group level behavior, including group dynamics and task
description? Can we extend existing languages such as GAPPS or the
subsumption architecture for robust control of a collection?
Domains: What are good and bad domains for studying interacting
robots? What is and isn't ``cheating''? Is central control to be
frowned on? Does communication have to be direct, or can it be
mediated? Is simulating some sensing and communication acceptable?
Active Perception: Do different sensory requirements arise
in collective robotics? How does sensing ability influence group
dynamics and vice versa?
Planning: To what extent should robots that could potentially
interact plan their actions and interactions? When is planning
a particularly good, or bad, idea? What forms should plans take,
and what algorithms lead to those forms of plans?
Communication: What is the role of communication in
interacting robots? What are appropriate forms of communication?
Modeling: How should robots model each other in their
domain? How are such models constructed and used?
Learning: How can we exploit group dynamics and interaction
in learning? Does cooperation or competition enhance or inhibit
learning?
Those wishing to present their work should submit 5 copies of a short
paper (approximately 5 pages) as well as a one-page statement of
research interests and bibliography. Those wishing to participate only
should submit 5 copies of a one-page research statement and
bibliography. All submissions should include an e-mail address, a
telephone number, and a mailing address. Prospective participants are
encouraged to contact members of the program committee with any
questions or comments.
Submissions should be sent to arrive by February 26, 1993 to:
Keiji Kanazawa
Department of Computer Science
University of British Columbia
6356 Agricultural Road
Vancouver, B.C., Canada V6T 1Z2
+1-604-822-3061 (tel)
The notification date for acceptances is April 1, 1993. The deadline
for final manuscripts for inclusion into working notes will be June 1,
1993.
* Conference Registration
Registration for the main conference of IJCAI-93 is required to
participate in a workshop. The registration fee for each workshop is
300FF (about US $60). Information about IJCAI-93 can be obtained from
the IJCAI mail server ijcai-serv@imag.fr with message body "send
General-infos".
* Program Committee
Ronald C. Arkin (arkin@cc.gatech.edu)
Rodney A. Brooks (brooks@ai.mit.edu)
Edmund Durfee (durfee@engin.umich.edu)
John Hallam (john@aifh.ed.ac.uk)
Keiji Kanazawa (kanazawa@cs.ubc.ca)
------------------------------
Date: Fri, 11 Dec 1992 08:03 GMT-0200
From: SABBATINI@CCVAX.UNICAMP.BR
Subject: Call for Papers: Intn'l Conf Biomedical Engineering Rio 94
From: Renato M.E. Sabbatini - SABBATINI@CCVAX.UNICAMP.BR
Date: December 11, 1992
Source: NIBNEWS - An Electronic Newsletter on Medical Informatics
PLEASE FORWARD
CALL FOR PAPERS
1994 WORLD CONGRESS ON MEDICAL PHYSICS AND
BIOMEDICAL ENGINEERING WILL BE IN RIO
Rio de Janeiro, one of the most beautiful cities in the world, will
host the next World Congress on Medical Physics and Biomedical
Engineering, 21-26 August 1994.
The 1994 World Congress, sponsored by the International Federation for
Medical and Biological Engineering (IFMBE), the International Organization
for Medical Physics (IOMP) and the International Union for Physical and
Engineering Sciences in Medicine (IUPESM), and hosted by the corresponding
Brazilian societies, is the first to take place in a developing country
and will certainly bring a major contribution to the growth of the area
in Latin America.
Major Scientific Topics:
Artificial Intelligence Neural Networks
Bioengineering and Biomechanics Nuclear Medicine
Clinical Engineering Physiological Measurements
Diagnostic Radiology Quality Assurance
Dosimetry Radiation Protection
Electrophysiology Radiobiology
Instrumentation Radiotherapy
MR Imaging Rehabilitation Engineering
Medical Informatics Sensors and Transducers
Medical Physics Signal Processing
Modeling and Simulation Technology Assessment
Metrology Ultrasound
There will be oral and poster presentations. Abstracts shall be submitted
on special forms before 20 November 1993. A technical exhibition of
products and services will take place during the congress. Several pre-
congress courses and tutorials have also been planned.
The venue and host city:
Blue seas, dazzling beaches and majestic mountains with lush green tropical
forests form a unique backdrop for a busy metropolis. A modern cosmopolitan
city where visitors immediately feel at home, surrounded by incomparable
natural beauty, Rio offers many attractions, entertainment and unending
possibilities of amusement with its museums, parks, historical sites,
nightclubs, "samba houses", folklore shows (including its famous carnival
bands and dance groups) and tourist spots, like the Christ statue and
the Sugar Loaf mountain. Rio's surrounding regions offer fantastic possi-
bilities of pre- and post-congress excursions to the high mountain regions,
with cool climate and European-style constructions, or to more than 600
km of white-sands beaches, or to the hundreds of paradisiac islands
teeming with wildlife. Rio is served by the largest international airport
in Latin America, with connections to all major cities in the world.
For lodging, it offers a wide variety of hotels, ranging from moderately
priced to luxurious five star hotels at seaside.
The Congress will take place in the modern and ample facilities of RioCentro
Convention Center, located in the beutiful beach and lake district of Barra
do Tijuca, near the famous Copacabana and Ipanema beaches.
Secretariat:
Congrex do Brasil. Rua do Ouvidor, 60/414, Rio de Janeiro, RJ 20040, Brazil
Phone: +55-21-224-6080, Fax: +55-21-231-1492, Telex: +55-21-32891
Send your name, institution, full address, postal code, phone, fax and
email address to the above, if you want to receive further announcements.
------------------------------
From: Andy Clark <andycl@syma.sussex.ac.uk>
Date: Tue, 15 Dec 92 16:43:25 GMT
bcc: andycl@cogs
re: Doctoral Program in Philosophy-Psychology-Neuroscience
First Announcement of a New Doctoral Programme in
PHILOSOPHY-NEUROSCIENCE-PSYCHOLOGY
at
Washington University in St. Louis
The Philosophy-Neuroscience-Psychology (PNP) program
offers a unique opportunity to combine advanced
philosophical studies with in-depth work in Neuroscience
or Psychology. In addition to meeting the usual requirements for
a Doctorate in Philosophy, students will spend one year working in
Neuroscience or Psychology. The Neuroscience option will draw
on the resources of the Washington University
School of Medicine which is an internationally acknowledged
center of excellence in neuroscientific research. The
initiative will also employ several new PNP related Philosophy faculty
and post-doctoral fellows.
Students admitted to the PNP program will embark
upon a five-year course of study designed to fulfill all the
requirements for the Ph.D. in philosophy, including an
academic year studying neuroscience at Washington
University's School of Medicine or psychology in the
Department of Psychology. Finally, each PNP student will
write a dissertation jointly directed by a philosopher and a
faculty member from either the medical school or the
psychology department.
THE FACULTY
Roger F. Gibson, Ph.D., Missouri, Professor and Chair:
Philosophy of Language, Epistemology, Quine
Robert B. Barrett, Ph.D., Johns Hopkins, Professor:
Pragmatism, Renaissance Science, Philosophy of Social
Science, Analytic Philosophy.
Andy Clark, Ph.D., Stirling, Visiting Professor (1993-6) and
Acting Director of PNP:
Philosophy of Cognitive Science, Philosophy of Mind,
Philosophy of Language, Connectionism.
J. Claude Evans, Ph.D., SUNY-Stony Brook, Associate Pro-
fessor: Modern Philosophy, Contemporary Continental
Philosophy, Phenomenology, Analytic Philosophy, Social and
Political Theory.
Marilyn A. Friedman, Ph.D., Western Ontario, Associate
Professor: Ethics, Social Philosophy, Feminist Theory.
William H. Gass, Ph.D., Cornell, Distinguished University
Professor of the Humanities: Philosophy of Literature,
Photography, Architecture.
Lucian W. Krukowski, Ph.D., Washington University, Pro-
fessor: 20th Century Aesthetics, Philosophy of Art,
18th and 19th Century Philosophy, Kant, Hegel,
Schopenhauer.
Josefa Toribio Mateas, Ph.D., Complutense University,
Assistant Professor: Philosophy of Language, Philosophy
of Mind.
Larry May, Ph.D., New School for Social Research, Pro-
fessor: Social and Political Philosophy, Philosophy of
Law, Moral and Legal Responsibility.
Stanley L. Paulson, Ph.D., Wisconsin, J.D., Harvard, Pro-
fessor: Philosophy of Law.
Mark Rollins, Ph.D., Columbia, Assistant Professor:
Philosophy of Mind, Epistemology, Philosophy of Science,
Neuroscience.
Jerome P. Schiller, Ph.D., Harvard, Professor: Ancient
Philosophy, Plato, Aristotle.
Joyce Trebilcot, Ph.D., California at Santa Barbara, Associ-
ate Professor: Feminist Philosophy.
Joseph S. Ullian, Ph.D., Harvard, Professor: Logic, Philos-
ophy of Mathematics, Philosophy of Language.
Richard A. Watson, Ph.D., Iowa, Professor: Modern Philoso-
phy, Descartes, Historical Sciences.
Carl P. Wellman, Ph.D., Harvard, Hortense and Tobias Lewin
Professor in the Humanities: Ethics, Philosophy of Law,
Legal and Moral Rights.
EMERITI
Richard H. Popkin, Ph.D., Columbia: History of Ideas,
Jewish Intellectual History.
Alfred J. Stenner, Ph.D., Michigan State: Philosophy of
Science, Epistemology, Philosophy of Language.
FINANCIAL SUPPORT
Students admitted to the Philosophy-Neuroscience-Psychology
(PNP) program are eligible for five years of full financial
support at competitive rates in the presence of satisfactory
academic progress.
APPLICATIONS
Application for admission to the Graduate School should be
made to:
Chair, Graduate Admissions
Department of Philosophy
Washington University
Campus Box 1073
One Brookings Drive
St. Louis, MO 63130-4899
Washington University encourages and gives full
consideration to all applicants for admission and financial
aid without regard to race, color, national origin,
handicap, sex, or religious creed. Services for students
with hearing, visual, orthopedic, learning, or other
disabilities are coordinated through the office of the
Assistant Dean for Special Services.
------------------------------
Date: Wed, 16 Dec 92 12:43:41 JST
From: degaris@etl.go.jp (Hugo de Garis)
Subject: SAB92 Report, Hugo de Garis (ETL, Japan)
Dear ALifers,
Here is a report on the recent SAB92 conference in Hawaii.
Hope you can use it in your ALife email network.
Cheers,
Hugo de Garis.
SAB92 Report
Simulation of Adaptive Behavior SAB92 Conference, Hawaii, 7-11 Dec 1992.
by
Hugo de Garis
Electrotechnical Lab (ETL)
Japan
Its hard to imagine a more beautiful setting for a conference than Hawaii.
As a postcard put it that I bought (showing moonlight reflecting off the water
silouetted by palm trees) "Just another ho hum day in paradise : Hawaii".
For many of us who attended this second SAB conference, it was our first visit
to Hawaii, so the 12 am to 4 pm "siesta" period was most welcome. However, the
beauty of the surroundings was offset by the distance to be travelled, hence
numbers were down (100 people, half of whom were presenters) and nearly all
were jet lagged, so the the first day or two were viewed through a mental
fog.
The first SAB conference was held in Paris in Dec 1990 where the dominant
theme seemed to be how ethologists and roboticists could help each other in
elucidating the secrets of behavioral mechanisms. Biologists were noticably
absent at this second SAB conference, dominated by computer and engineering
types. This is probably to be expected as the field matures. The conference had
a feel of "more of the same" rather than of the excitement of the "qualitativelynew" of the first conference. I guess you have to be a Chris Langton to be able
to make successive conferences exciting. Still, one came away with the
impression that some solid progress had been made since the Paris conference.
The most impressive example is the appearance of a new MIT Press journal,
"Adaptive Behavior", edited by the Frenchman, Jean-Arcady Meyer. Jean-Arcady
and future SAB conference organizers now face the difficult task of defining
a niche for the field which is narrow enough to distinguish itself from
the highly overlapping fields of Neural Networks, Genetic Algorithms,
Artificial Life, Parallel Problem Solving from Nature (PPSN), Robotics, etc
yet not be so narrow that the field becomes overdefined and stagnates.
Roughly 40 oral and 20 poster papers were presented, with the following
themes.
The Animat Approach to Adaptive Behavior.
Perception and Motor Control.
Action Selection and Behavioral Sequences.
Cognitive Maps and Internal World Models.
Learning.
Evolution.
Collective Behavior.
Highlights were (according to my own subjective view and that of one of the
organizers) :-
Pattie Maes's talk on "Behavior Based Artificial Intelligence" (the
first talk of the conference) which made the point that behavior based
thinking should be extended beyond robotics to AI in general, but was
more a statement of intent than of concrete results. Pattie's
productivity seems to have dropped since she became an assistant prof
at MIT. Its a pity that Europe and the US do not give enough "research
only" positions to its best researchers. If the West doesnt watch out,
it will lose its best to Japan, which has more sense that way by
creating many positions with no teaching load. Quoting Pattie's
abstract - "This paper attempts to define Behavior-Based Artificial
Intelligence (AI) as a new approach to the study of intelligence. It
distinguishes this approach from the traditional knowledge based
approach in terms of the questions studied, the solutions adopted and
the criteria used for success. It does not limit behavior based AI to
the study of robots but rather presents it as a general approach for
building autonomous systems that have to deal with multiple, changing
goals in a dynamic, unpredictable environment".
Mark Ring's (Univ. of Texas) paper "Two Methods for Hierarachy Learning in
Reinforcement Environments". His abstract read - "This paper describes two
methods for hierarchically organizing temporal behaviors. The first is more
intuitive : grouping together common sequences of events into single units
so that they may be treated as individual behaviors. This system immediately
encounters problems however, because the units are binary, meaning
the behaviors must execute completely or not at all, and this hinders the
construction of good algorithms. The system also runs into difficulty when
more than one unit is (or should be) active at the same time. The second system
is a hierarchy of transition values. This hierarchy dynamically modifies the
values that specify the degree to which one unit should follow another. These
values are continuous, allowing the use of gradient descent during learning.
Furthermore, many units are active at the same time as part of the system's
normal functioning".
Michael Littman's (Bellcore, CMU) paper "An Optimization-based Categorization
of Reinforcement Learning". Abstract - "This paper proposes a categorization
of reinforcement learning environments based on the optimization of a
reinforcement signal over time. Environments are classified by the simplest
agent that can possibly achieve optimal reinforcement. Two parameters, h and
beta, abstractly characterize the complexity of an agent: the ideal (h, beta)-
agent uses the input information provided by the environment and at most h bits
of local storage to choose an action that maximises the discounted sum of the
next beta reinforcements. In an (h, beta)-environment, an ideal (h, beta)-agent
achieves the maximum possible expected reinforcement for that environment. The
paper discusses the special cases when either h = 0 or beta = 1 in detail,
describes some theoretical bounds on h and beta and re explores a well known
reinforcement learning environment with this new notation".
Jing Peng's and Ronald William's (Northeastern Univ) paper "Efficient Learning
and Planning within the Dyna Framework". Abstract -
"Sutton's Dyna framework provides a novel and computationally appealing way to
integrate learning, planning and reacting in autonomous agents. Examined here
is a class of strategies designed to enhance the learning and planning power
of Dyna systems by increasing their computational efficiency. The benefit of
using these strategies is demonstrated on some simple abstract learning tasks".
Dave Cliff's et al (Sussex) paper "Evolving Visually Guided Robots" appealed
most strongly to me, because it used (evolved) neural networks to control
robots (my own line of work). Dave evolved a neural network which took visual
input to control the motion of a robot. His abstract was too long to quote.
Hitoshi Iba (a colleague at ETL) presented a paper called "Evolutionary Learning
of Predatory Behaviors Based on Structured Classifiers". Iba san has done some
innovative work in extending Koza's Genetic Programming Paradigm (i.e.
evolving tree structured Lisp programs) into Holland's Classifier Systems,
and applying the results to the optimization of animal foraging strategies.
Geoffrey Miller's (Stanford) and Peter Todd's (Rowland Inst) paper "EvolutionaryInteractions among Mate Choice, Speciation, and Runaway Sexual Selection".
This paper explored the effects of different mate choice mechanisms and modes
of speciation on the dynamics of runaway sexual selection. Geoffrey showed how
sexual selection could cause fitness levels to deviate from optimal values.
Long-Ji Lin's and Tom Mitchell's (CMU) paper "Reinforcement Learning with
Hidden States". Abstract - "Reinforcement learning is an unsupervised learning
technique for sequential decision making. Q-learning is a widely used
reinforcement learning method. The convergence of Q-learning relies on the
Markovian environment assumption, meaning that any information needed to
determine the optimal action is reflected in the agents state representation.
If some important state features are missing (or hidden) from the state
representation, the true world states cannot be directly identified and optimal
decisions cannot be made based on this state representation. This problem is
known as the hidden state problem. A possible solution to the problem is to use
history information to help uncover the hidden features. This paper studies
3 reinforcemnt learning architectures that learn to use history to handle hiddenstates: window-Q, recurrent-Q, and recurrent model. Empirical study of these
architectures is presented. Their relative strengths and weaknesses are also
discussed."
Harry Klopf's (Wright Lab) "Modelling Nervous System Function with a
Hierarchical Network of Control Systems that Learn". (Part of) Abstract -
"A computational model of nervous system function during classical and
instrumental conditioning is proposed. The model assumes the form of a
hierarchical network of control systems. Each control system is capable of
learning and is referred to as an associative control process (ACP). Learning
systems consisting of ACP networks, employing the drive reinforcement learning
mechanism (Klopf 1988) and engaging in real time, closed loop, goal seeking
interactions with environments, are capable of being classically and
instrumentally conditioned, as demonstrated by means of computer simulations".
This paper felt important, and that it made more than the usual incremental
contribution to the field. Klopf's neural network hierarchies actually LEARN.
If there had been a best paper award, my vote would have gone to Klopf.
*** End of Highlights ***
Now for the down side. I found it most annoying that there was no proceedings
ready at the conference. This was a point discussed in the feedback session
on the second last day. The organizers said they would try to remedy this fault
at SAB94 (which will be held very probably in the first week of August, at
the University of Sussex, Brighton, England). There seems to be a growing
tendency for conference organizers not to bother having a proceedings ready in
time for the conference. The worst offender in this regard, is Chris Langton,
who manages to come out with a book, a year after the conference, and worse,
half of the oral papers do not even appear in the book, so these poor guys
dont even get published. I would like to go on record as stating that
conference organizers who do not bother having a proceedings in time for
their conferences, should be BOILED IN OIL. (The SAB92 proceedings will be
published by MIT Press and should appear in the spring of 93).
See you at SAB94 in Brighton, England.
Hugo de Garis.
------------------------------
End of ALife Digest
*******************
