July 1997
|
This file is a list of items added to the UMBC agents pages this month
and is in maintained chronological order.
1999:
July,
1998:
Jan,
Feb,
Mar,
Apr,
May,
June,
July,
Aug,
1997:
Jan,
Feb,
Mar,
Apr,
May,
June,
July,
Aug,
Sept,
Oct,
Nov,
Dec,
1996:
Jan,
Feb,
Mar,
Apr,
May,
June,
July,
Aug,
Sept,
Oct,
Nov,
Dec,
1995:
Aug,
Sept,
Oct,
Nov,
Dec.
|
WiseWire
|
WiseWire is a Web service that
grew out of Newsweeder project at CMU. It uses neural nets and
collaborative filtering to train a "Wire" to deliver high quality
online information (from the web, newswire articles, Usenet
newsgroups, and mailing lists) that can be tailored to a person's
interests. A "wire" is a collection of documents pertaining to a
particular topic. WiseWire has a set of intial "community wires" that
can be read by anyone, which can be "personalised" for an individual
user. Users evaluate content items using a simple graphical rating
bar, providing ratings which allow a Wire to learn preferences and
deliver better quality information. WiseWire leverages the feedback
of whole communities through collaborative filtering, which assumes
that content rated highly by one person is likely to be rated highly
by people with similar interests.
7/15/97
|
Beady-eyed agents
|
The BDI model of agency provides a powerful organizing framework on
which to build software agents. Two recent papers are:
There are also some recent books which explicate the BDI approach:
- MULTIAGENT
SYSTEMS, A Theoretical Framework for Intentions, Know-How, and
Communications Munindar P. Singh, Springer-Verlag, Lecture Notes
in Computer Science, Volume 799, (subseries: Lecture Notes in
Artificial Intelligence), ISBN 0-387-58026-3 (North America), ISBN
3-540-58026-3 (elsewhere), xxiii+168 pages, softback. List price: DM
46.00 or USD 33.00. This book develops a semantics for two primitives
-- intentions and know-how -- in a general model of actions and time.
... The proposed framework involves actions, possible and actual,
abstract and concrete, that agents perform. This enables one to use
intentions, know-how, and communications in stating constraints on
system behavior that more naturally capture users' requirements. The
proposed framework can thus serve as a foundation on which to develop
specific approaches and methodologies for specifying, designing, and
implementing complex systems.
-
7/8/97
|
AI Journal issue on agents
|
The journal Artificial
Intelligence has a special issue (Volume 94, Issue 1, 20-July-1997)
devoted to agents. The articles include:
- David Poole,
The independent choice logic for modelling multiple agents under
uncertainty, Artificial Intelligence (94)1 (1997) pp. 7-56.
- Stuart J. Russell,
Rationality and intelligence, Artificial Intelligence (94)1 (1997)
pp. 57-77.
- Sarit Kraus, Negotiation
and cooperation in multi-agent environments, Artificial
Intelligence (94)1 (1997) pp. 79-97.
- Tuomas W. Sandholm, Victor R. Lesser, Coalitions
among computationally bounded agents, Artificial Intelligence
(94)1 (1997) pp. 99-137.
- Yoav Shoham, Moshe Tennenholtz, On
the emergence of social conventions: modeling, analysis, and
simulations, Artificial Intelligence (94)1 (1997) pp. 139-166.
- Daphne Koller, Avi Pfeffer, Representations
and solutions for game-theoretic problems, Artificial Intelligence
(94)1 (1997) pp. 167-215.
- Ronen I. Brafman, Moshe Tennenholtz, Modeling
agents as qualitative decision makers, Artificial Intelligence
(94)1 (1997) pp. 217-268.
Full copies of the articles in postscript are available to individuals
who have subscriptions or are associated with an organization which
has a subscription.
7/8/97
|
On-line proceedings of UM'97
|
The complete proceedings of UM97, the Sixth International
Conference on User Modeling (held June 2-6, 1997) is available at User Modeling, Inc. It
includes approximately 400 pages of edited manuscripts, including: 28
12-page full papers, fifteen three-page poster summaries, extended
abstracts of invited talks and doctoral consortium presentations.
Together, these manuscripts offer a representative sample of current
research into user modeling, in which ways of enabling interactive
software systems to adapt to their users are investigated. The
printed proceedings volume will published by Springer Wien New York.
7/2/97
|
Dartmouth Workshop on Transportable Agents
|
The Second
Dartmouth Workshop on Transportable Agents will be held September
19-20, 1997 at Dartmouth College in Hanover, NH.
The workshop will bring together researchers from three technical
communities -- artificial intelligence, distributed systems, and
programming languages -- to define a unified long-term vision and a
short-term list of scientific challenges. The workshop begins on
Friday evening with a keynote speech by John Ousterhout (Sun
Microsystems), followed by a reception. On Saturday, topical
discussions will be led by Joel Saltz (UMD), James White (Telescript),
Thomas Sandholm (Washington University), Tim Finin (UMBC), Greg
Jorstad (Lockheed-Martin), Victor Lesser (UMass), and Mark Wellman
(U. Michigan). Those interested in attending should submit by
September 1, 1997 a one-page abstract describing your interest in
transportable agents, a short bio of each potential attendee from your
project and an indication of whether you would like to present a
poster at the Saturday-night reception. 7/1/97
|