|
|
|
|
|
"Animals are not just herbivores or carnivores. They are, in a nice
coinage of the psychologist George Miller, informavores. And
they get their epistemic hunger from the combination, in exquisite
organization, of the specific epistemic hunger of millions of
microagents, organized into dozens or hundreds or thousands of
subsystems. Each of these tiny agents can be conceived of as an
utterly minimal intentional system, whose life project is to ask a
single question, over and over and over -- "Is my message coming in
NOW?" "Is my message coming in NOW?" -- and springing into limited
but appropriate action whenever the answer is YES."
-- Daniel Dennett, Kinds of Minds.
|
THIS ISSUE |
Volume 1,Number 10
July 22, 1996
Baltimore, MD
|
http://www.cs.umbc.edu/agents/agentnews/1996/10/
Modified Wednesday, 31-Jul-1996 19:54:28 EDT
|
AGENT NEWS |
Intelligent Agents = Stupid Humans?
|
Wired magazine is sponsoring a web-based debate between Pattie Maes
and Jaron Lanier on Intelligent
Agents = Stupid Humans? which deals with the feasibility and
desirability of intelligent agents. The debate consists of daily
comments and responses from the participant between June 15 and June
24 and also includes a forum for ongoing comments from observers.
This is the latest debate in Wired's "Brain Tennis" series which
previously has featured "the Web as a perpetually unprofitable
publishing medium", "the end of science", and "journalistic
objectivity". The two are starting from somewhat different
perspectives:
- Pattie Maes: "Agents will bring about a social revolution: almost
anyone will have access to the kind of support staff that today is the
mark of a few privileged people. As a result, they will be able to
digest large amounts of information and engage in several different
activities at once."
- Jaron Lanier: "The idea of 'intelligent agents' is both wrong and
evil. I also believe that this is an issue of real consequence to the
near-term future of culture and society. As the infobahn rears its
gargantuan head, the agent question looms as a deciding factor in
whether this new beast will be much better than TV, or much worse."
|
AGENT TECHNOLOGY |
IBM's Aglets library
|
IBM Tokyo Research Laboratory is making available
an early release of their Aglets Library for programming mobile agents
in Java(tm). The package is based on JDK 1.0.2 and Object
Serialization in the RMI package from JavaSoft. The first beta release
includes Java packages, documentation, and a demo applications.
|
Tcl Plug-ins for Netscape Navigator
|
Sun has released Tcl Plug-ins
for Netscape Navigator, making it possible to create Web pages that
include Tcl/Tk scripts. This provides an interesting alternative to
the use of Java applets for Web-based agent programs. Ray Johnson
says "Tcl/Tk complements the capabilities of Java. While Java is a
system programming language that meets the needs of sophisticated
programmers with features such as objects, threads, and rich class
libraries, Tcl/Tk is a scripting language that is ideal for smaller
applications, such as simple user interfaces, macros, and system
integration." Sun's current version of the Tcl plug-in runs only with
Netscape Navigator under Solaris, Macintosh, and Windows with support
for other browsers and operating systems planned.
|
Java Agent Template
|
Java
Agent Template, Version 0.3, is now available. The JAT provides a
fully functional template, written entirely in the Java language, for
constructing KQML-speaking software agents which communicate
peer-to-peer with a community of other agents distributed over the
Internet. The JAT includes functionality for dynamically exchanging
"Resources", which can include Java classes (e.g. new languages and
interpreters, remote services, etc.), data files and information
inlined into the KQML messages. JAT agents can be executed as either
stand alone applications or as applets via the appletviewer.
|
|
Swarm is a
software package for multi-agent simulation of complex systems being
developed at The Santa Fe Institute. Swarm is intended to be a useful
tool for researchers in a variety of disciplines, especially
artificial life. The basic architecture of Swarm is the simulation of
collections of concurrently interacting agents: with this
architecture, we can implement a large variety of agent based models.
Swarm runs on Unix machines running GNU Objective C and X windows.
The beta release is available for download to the general public and
source code is freely available under GNU Licensing
terms.
|
|
Agentsheets
is an authoring environment developed by Alex Repenning at the
University of Colorado at Boulder. It features a versatile
construction paradigm to build dynamic, visual environments for a wide
range of problem domains such as art, artificial life, distributed
artificial intelligence, education, environmental design,
object-oriented programming, simulation and visual programming. The
construction paradigm consists of a large number of autonomous,
communicating agents organized in a grid, called the
agentsheet. Agents can use different communication modalities such as
animation, sound and speech. Agentsheets is written in Macintosh
Common LISP (MCL 2.0) and is available from the author.
|
Java classes for intelligent agents
 | Bits & Pixels's Java
Intelligent Agent Library ($179) provides components for building
intelligent agents, implemented entirely in Java. The library is a
collection of over 150 java classes covering various aspects of
building intelligent agents. In addition to agent communication and
data handling facilities, the library contains rule-based and neural
net-based processing modules. There is also an extensive modeling
facility for prototyping agent interactions and graphical classes for
creating static and animated interactive displays.
|
AGENTS ON THE NET |
Cave automata
|
xxx.lanl.gov's web administrators complain of
``"intelligent agents" (a.k.a. "robots") that mindlessly download
every link encountered, ultimately trying to access the entire
database through the listings links.''. They have followed the
proposed standard for robot exclusion by maintaining a file
/robots.txt specifying the URL's that are off-limits to
robots, but this has not been effective. So, to protect themselves,
they have set a robot trap (at
http://xxx.lanl.gov/seek-and-destroy -- caution: do not visit
this page). They say ``We are not willing to play sitting duck to
nonsensical methods of "indexing" information. This server is
configured to monitor activity and deny access to sites that violate
the above guidelines. Continued rapid-fire requests from any site
after access has been denied (i.e. with 403 Access denied HTTP
response) will be interpreted as a network attack; and we will respond
accordingly --- without hesitation, and without further warning.''.
|
SUMPY maintains Unix file systems
|
SUMPY:
A Fuzzy Software Agent, Hongjun Song, Stan Franklin, and Aregahegn
Negatu, Proceedings of the international conference on intelligent
systems, Reno, Nevada, June 19-21, 1996. Abstract: SUMPY is a
software agent "living" in and helping to maintain a UNIX file system
for better disk space utilization by compressing and backing up
files. Built using subsumption architecture, SUMPY displays a "plug
and play" property. A new UNIX maintenance task can be added to
SUMPY's repertoire without modification of existing layers. One of
SUMPY's layers sports a fuzzy control mechanism enabling it to achieve
its goals in a real-world manner. Another restricts SUMPY's activity
to times of slow CPU use. An experiment in agent architecture and in
the use of agents for such maintenance tasks, SUMPY promises to prove
useful, and has added no significant problems to the test systems.
|
Will this agent help you "get a life"?
|
LifestyleFinder
is an intelligent agent developed by Bruce Krulwich of Andersen
Consulting. It was tested on Friday, July 19th, between 10am and 12
noon Central (Chicago) time. They expect to launch LifestyleFinder
for real on July 29th, and are testing it now for accuracy and for
system load. No word on what it will do, but check out
"http://bf.cstar.ac.com/bf/lifestylefinder" once it is released to
find out.
|
AGENT BUSINESS |
|
|
Agent Knowledgebase Associates is a
Virginia Beach based company specializing in "Knowledge Management,
Information Agents and WWW Advertising".
|
AGENT RESOURCES |
Autonomous characters |
Characters,
improvisation, and... is Craig Reynolds's
collection of references to autonomous characters that can improvise
and react to their environment.
|
Computists International
|
Computists International is an
AI-research-oriented mutual-aid association which publishes highly
condensed email newsletters: the twice-weekly Computists' Communique
(TCC) and the weekly Computists' Career Jobs (CCJ), Computists'
Applied Jobs (CAJ), and Computists' Research Software (CRS). TCC has
been published by Dr. Kenneth I. Laws (laws@computists.com) since 1991
and includes information on grant and funding opportunities; industry
news; Internet and Web news; online resources; research discussion
lists; news and software offers in AI, neural networks, genetic
algorithms, machine learning, pattern recognition, text understanding,
NLP, etc.; software development resources; and career or
entrepreneurial tips.
|
AGENTS IN PRINT |
|
Turtles, Termites, and Traffic Jams, Explorations in Massively
Parallel Microworlds, Mitchel Resnick, 1994, Complex Adaptive
Systems series. MIT Press, A Bradford Book, ISBN 0-262-18162-2, 192
pp., $24.95 (cloth). Resnick discusses decentralized systems of
agents, self-organizing phenomena and their simulation using the
massively parallel programming language StarLogo. StarLogo
is a programmable modeling environment specially designed to allow
students to explore the behaviors of decentralized systems, such as
bird flocks, traffic jams, and ant colonies. StarLogo can be
downloaded from the Internet without cost.
|
Architectures for human-like agents
|
What
sort of architecture is required for a human-like agent?, Aaron
Sloman, The University of Birmingham. Invited talk at Cognitive
Modeling Workshop, AAAI96, Portland Oregon, Aug 1996. Abstract: This
paper is about how to give human-like powers to complete agents. For
this the most important design choice concerns the overall
architecture. Questions regarding detailed mechanisms, forms of
representations, inference capabilities, knowledge etc. are best
addressed in the context of a global architecture in which different
design decisions need to be linked. Such a design would assemble
various kinds of functionality into a complete coherent working
system, in which there are many concurrent, partly independent, partly
mutually supportive, partly potentially incompatible processes,
addressing a multitude of issues on different time scales, including
asynchronous, concurrent, motive generators. Designing human like
agents is part of the more general problem of understanding design
space, niche space and their interrelations, for, in the abstract,
there is no one optimal design, as biological diversity on earth
shows.
|
Intelligent Software Agents on
the Internet
|
Intelligent Software Agents
on the Internet: an inventory of currently offered functionality
in the information society & a prediction of (near-)future
developments" Bjorn Hermans, Tilburg University, Tilburg, The
Netherlands. Abstract: Software agents are a rapidly developing area
of research. However, to many it is unclear what agents are and what
they can (and maybe cannot) do. In the first part, this thesis will
provide an overview of these, and many other agent-related theoretical
and practical aspects. Besides that, a model is presented which will
enhance and extend agents' abilities, but will also improve the way
the Internet can be used to obtain or offer information and services
on it. The second part is all about trends and developments. On the
basis of past and present developments of the most important, relevant
and involved parties and factors, future trends and developments are
extrapolated and predicted.
|
Personal agents: A walk on the client side
|
Personal
agents: A walk on the client side, P. J. Kearney,
Real-World Applications of Intelligent Agent Technology seminar
London, June 1996, Unicom. This paper will also be presented at the
IBC Seminar on Intelligent Agents, London June 1996. An earlier
version was presented at the IEE Professional Group C3 Colloquium on
Intelligent Agents and their applications, April 1996. Digest No:
1996/101, Distributed Intelligent Systems, Sharp Laboratories of
Europe Ltd. Oxford, UK. Abstract: The world is fast becoming a giant
heterogeneous information system in which personal electronics
products (including PDAs, PCs, set-top-boxes, etc.) play a key
role. The vast number and diversity of the components and uses of the
system necessitates a decentralized, emergent organization. The agent
metaphor offers an attractive route to achieving such an
organization. In this paper, I outline the role of agent software in
personal electronics in mediating between the individual user and the
available services and project a likely sequence in which personal
agent-based products will be successful. I also discuss various
standardization and interoperability issues affecting the practicality
of agents in this role.
|
Network-aware mobile programs
|
Network-aware Mobile Programs, M. Ranganathan,
Anurag Acharya, Shamik Sharma, Joel Saltz, Submitted for USENIX'97.
Abstract: In this paper, we investigate network-aware
mobile programs, programs that can use mobility as a tool to adapt to
variations in network characteristics. We present infrastructural
support for mobility and network monitoring and show how
adaptalk, a Java-based mobile Internet chat application can
take advantage of this support to dynamically place the chat server so
as to minimize response time. Our conclusion was that on-line network
monitoring and adaptive placement of shared data-structures can
significantly improve performance of distributed applications on the
Internet. |
Resource monitoring for mobile objects
|
Distributed
Resource Monitors for Mobile Objects, M. Ranganathan,
Anurag Acharya, Joel Saltz, Position paper submitted to IWOOOS'96.
Abstract: We present our position on resource monitoring as three
working hypotheses. First, a resource-aware placement of components of
a distributed application can provide significant performance gains
over a resource-oblivious placement. Second, effective mobility
decisions can be based on coarse-grained monitoring. Finally, a simple
and cheap distributed resource monitoring scheme can provide
sufficient information for effective mobility decisions. We present a
design for distributed resource monitors which we believe can provide
effective resource information at an acceptable cost. |
AGENT EVENTS |
ICMAS'96 Workshop:
Learning, Interaction and Organizations in Multiagent Environments
|
Learning, Interaction and Organizations in Multiagent
Environments, ICMAS'96 Workshop, December 10th, 1996.
Extended abstracts due August 25. This workshop FOCUSES on the
relationships between learning, interaction and organizations in
multiagent environments. The need for studying these relationships is
twofold. On the one hand, the efficiency and the success of a
multiagent system largely depends on how efficient and successful the
individual agents interact. On the other hand, even in simplified
application domains it is almost impossible to correctly specify
appropriate interactions between the individual agents a priori, and
it is therefore desirable that the agents themselves are capable of
learning to interact appropriately. The workshop is INTENDED to cover
the whole range of open questions and problems concerning these
relationships in all types of multiagent systems (e.g., robots
interacting with dynamic environments, multiple robot systems, systems
composed of interacting software agents, hybrid systems composed of
both interacting humans and machines). A major GOAL of the workshop is
to get a better understanding of how learning can improve the
interactivity between agents embedded in multiagent environments.
|
ICMAS'96 Workshop -- Animal societies as a DAI metaphor
|
Animal
societies as an alternative metaphor basis for Distributed
Artificial Intelligence , an ICMAS'96 Workshop, December 10th,
1996 (Keihanna Plaza, Kyoto, Japan). Scope: When designing
computational organizations, DAI research generally gives more
attention to sociological metaphors than to biological ones. However,
it is worth noting that most of the issues being addressed in DAI
(e.g., cooperation, coordination, organization, social interaction)
have a significant intersection with the goals and interests of a
variety of research communities (ethology, primatology, behavioral
ecology, or artificial life) that study the social mechanisms that
occur in non-human societies - i.e. animal societies. |
AGENTNEWS NEWS |
AgentWeb Salon opens
|
AgentWeb salon
is a Java-based on-line chat room for people and agents interested in
real-time interactions. It is implemented with the alpha version of
JavaTalk!, an
interactive web (java) based chat.
|
1300+ subscribers
AgentNews WebLetter now has over 1300 email subscribers. The
ASCII version is still the most popular but more and more people are
signing up for the HTML or URL version. So far, only two agents have
elected to receive it via KQML.
|
|
[an error occurred while processing this directive]