*** EXTENDED SUBMISSION DEADLINE: MARCH 15 ***
[Please forward to anyone who may be interested]
[Apologies if you receive multiple copies]
______________________________________________________________________
LAST CALL for PAPERS
Special Session on "Learning and Adapting in AI Planning"
at IC-AI 2001
Las Vegas, Nevada, USA, June 25-28, 2001
http://mcs.open.ac.uk/mg343/AI-session.htm
________________________________________________________________________
A Special Session on "Learning and Adapting in AI Planning" will take place
at the Monte Carlo Resort in Las Vegas, Nevada (USA), during June 25-28, as
part of the 2001 International Conference on Artificial Intelligence
(IC-AI'2001, held in conjunction with the International Multiconference:
http://www.ashland.edu/~iajwa/conferences/).
Scope and Overview:
------------------
The past few years have seen dramatic advances in planning algorithms and
paradigms. Recent systems can quickly solve problems that are orders of
magnitude harder than those tackled by the best previous planners. However,
if planning systems are to find wide application in real-world situations,
they need to be able to offer good quality, real-time performances over a
large range of problems. The thesis underlying this session is that in order
to do so, not only must planners be fast, but also be flexible and able to
adapt automatically to different problems and domains.
Two current approaches tackling this issue from different perspectives are:
1) the automatic extraction of domain-specific knowledge through domain
analysis, and 2) the acquisition of domain-specific or search-control
knowledge and procedural abstractions through the employment of learning
techniques. In order to discuss the state of the art of these areas of
research and stimulate their cross-fertilisation, we invite submissions of
papers on one or both of these approaches. More specifically, topics of
particular interest concern the development of planning systems or
algorithms that can learn from past experience, and/or automatically analyse
and adapt to new problem domains, in order to 1) offer good performances
over a wide range of different situations or 2) improve efficiency or plan
quality on the basis of failures and successes.
Topics will include (but not be limited to):
- inference of invariants through domain analysis and hypothesis testing;
- acquisition of domain knowledge in incomplete or inaccurate domains;
- acquisition of strategies for action selection;
- acquisition of heuristics for state-space or plan-space search;
- learning control knowledge;
- learning macro-operators;
- learning plan-rewriting rules;
- reinforcement learning for conformant and stochastic planning;
- integration of planning, learning and execution;
and, in general, the use of any learning technique (such as
explanation-based, inductive, supervised, analytic or by-analogy learning)
for improvement and optimisation of current state-of-the-art planning
systems.
Formatting Instructions:
-----------------------
Prospective authors are invited to submit draft papers of about 4 or 5
single-spaced A4 pages. The first page of the draft should include: title of
the paper, abstract (100-150 words), name, affiliation, postal address,
telephone number, Fax and e-mail address of each author. The first page
should also specify the name of the Contact Author and a maximum of 5
keywords. The length of the Camera-Ready papers (if accepted) will be
limited to 7 pages. We strongly encourage the use of LaTeX for the
preparation of papers; other formats are likely to be troublesome. (The
typesetting instructions used last year for the preparation of IC-AI'2000
Camera-Ready papers are available at:
http://mcs.open.ac.uk/mg343/Doc/typing.htm. However, for submissions of
draft papers, other similar and reasonable formats will also be accepted.)
Submission Guidelines:
---------------------
Papers must not have been previously published or currently submitted for
publication elsewhere. Electronic submission is STRONGLY recommended. Papers
should be submitted in (g)zipped PostScript/PDF format and be named
"author.zip", using the name of the Contact Author. To submit a paper, email
it (or a URL pointer to it) to the Session Chair, Dr. Max Garagnani
([log in to unmask]) by ** MARCH 15, 2001 **. Notification of acceptance
or rejection of submitted papers will be sent to the e-mail address of the
Contact Author by April 1, 2001. If electronic submission is not
possible, THREE hard copies should reach the Session Chair (see address
below) by the same date. Notice that the final version of accepted papers
may be required to be produced in PostScript, PDF, or source form.
Evaluation Process:
------------------
Papers will be evaluated for originality, relevance, significance, soundness
and clarity. Each paper will be refereed by (at least) two researchers in
the topical area; written reviews will be returned to authors. The
Camera-Ready papers will be reviewed by one person. Accepted papers are
expected to be presented at IC-AI 2001 during the Special Session.
Publication:
-----------
Accepted papers will be published under the title of the Session in the
IC-AI 2001 Conference Proceedings. The Proceedings will be published by
CSREA Press (ISBN) in hardcopy and will be available at the Conference.
After the conference, some Sessions will be considered for publication as
Special Issues in appropriate journals.
Important Dates:
---------------
- March 15, 2001 (Thursday): Draft papers (about 4 to 5 pages) due
- April 1, 2001 (Sunday): Notification of acceptance/rejection
- May 1, 2001 (Tuesday): Camera-Ready papers and Pre-registration due
- June 25 - 28, 2001: Special Session & IC-AI Conference
Location:
--------
The Special Session will be held in the Monte Carlo Resort Hotel, Las Vegas,
Nevada, USA. This is a mega hotel with excellent conference facilities and
over 3,000 rooms. The Hotel is minutes from the Las Vegas airport, and
offers many vacation and recreational attractions, including: waterfalls,
casino, spa, pools & kiddie pools, sunning decks, Easy River water ride,
wave pool with cascades, lighted tennis courts, health spa (with workout
equipment, whirlpool, sauna, ...), arcade virtual reality game rooms,
nightly shows, snack bars, a number of restaurants, shopping area, bars, ...
Many of these attractions are open 24 hours a day and most are suitable for
families and children. The negotiated hotel's room rate for conference
attendees is very reasonable (79USD + tax) per night (no extra charge for
double occupancy) for the duration of the conference.
Program Committee & Contact Information:
---------------------------------------
Ricardo Aler Mur, Universidad Carlos III de Madrid (Spain)
Mike Barley, University of Auckland (New Zealand)
Jim Blythe, USC/Information Science Institute (USA)
Barbara Engelhardt, Jet Propulsion Laboratory (USA)
Maria Fox, University of Durham (UK)
Alfonso Gerevini, University of Brescia (Italy)
Karen Haigh, Honeywell Technology Center (USA)
Randolph M. Jones, Colby College and Soar Technology, Inc. (USA)
Henry Kautz, University of Washington, Seattle (USA)
Sven Koenig, Georgia Institute of Technology (USA)
John Levine, University of Edinburgh (UK)
Derek Long, University of Durham (UK)
Lee McCluskey, University of Huddersfield (UK)
Peter Stone, AT&T Labs (USA)
All submissions, queries or comments should be mailed or e-mailed to the
Session Chair:
Dr. Max Garagnani
Department of Computing
The Open University,
Walton Hall, Milton Keynes
MK7 6AA
U.K.
Phone: +44 (0)1908 654812
Secr.: +44 (0)1908 653037
Fax: +44 (0)1908 652140
E-mail: [log in to unmask]
URL: http://mcs.open.ac.uk/mg343
************************************************************************
