The AAAI 2006 workshop on
Learning for Search
Sunday July 16, 2006, Boston, Massachusetts

Workshop Description  Workshop Schedule  Important Dates  Submission Procedure  Contact information


AAAI will provide 30 by 40 inch foamcore boards for the poster session.
The workshop schedule is now available.

Workshop Description

Heuristic search is among the most widely used techniques in AI. In its different varieties, tree-based search and local search, it provides the core engine for applications as diverse as planning, parsing, and protein folding. One of the most promising avenues for developing improved search techniques is to integrate learning components that can adaptively guide the search.
Many disparate techniques have arisen in recent years that exploit learning to improve search and problem-solving. These techniques can be off-line or on-line, based on hard constraints or probabilistic biases, and applied to tree-structured or local search. This workshop aims to bring together researchers and practitioners from the various subcommunities where such methods have arisen in order to learn from each other, develop common understandings, and inspire new algorithms and approaches.

Relevant topics include, but are not limited to:

  • adaptive and self-tuning algorithms
  • automated parameter tuning
  • automated portfolio design
  • clause learning
  • computing search space features
  • decision-theoretic approaches to learning in search
  • dynamic portfolio design
  • exploiting models of search spaces
  • exploiting performance profiles or run-time distributions
  • incremental and active learning in search
  • learning to select operators or heuristic functions
  • model-based search
  • reinforcement learning for search algorithms
  • runtime prediction
  • uncertainty in runtime prediction

This one day workshop is organised by Wheeler Ruml and Frank Hutter.

Important dates

Note: Due to a request by AAAI to accept submissions until after the notification date for the AAAI technical program,
the general submission deadline for this workshop was extended to April 17 (3 days after the notification date).

Submission deadline: Monday, April 17, 2006
5pm PST (Pacific standard time)
(was March 31, 2006)
Notification of acceptance: May 3, 2006
(was April 24, 2006)
Camera-ready copy deadline: May 17, 2006 (unchanged)
AAAI early registration deadline: May 19, 2006
AAAI late registration deadline: June 16, 2006
Our Workshop: July 16, 2006
Other workshops: July 16/17, 2006
AAAI conference: July 16-20, 2006

Submission procedure

We ask authors to submit technical papers either in Postscript or PDF. Papers should be in AAAI conference style (formatting instructions available at: and are encouraged to be 6 pages in length with a maximum of 8 pages Please submit papers via email to

Please note that all submitted papers will be carefully peer-reviewed by multiple reviewers, and that low-quality or off-topic papers will not be accepted.
Also note that all workshop participants must register for the main AAAI-06 conference


Authors of accepted papers will automatically be invited. Other invitations will be sent on a personal/request basis.


Due to the large number of submissions we will have a poster session next to a number of short talks. See the schedule for details.

Contact information

Wheeler Ruml
Palo Alto Research Center, Room 2546
3333 Coyote Hill Road
Palo Alto, CA 94304-1314

650-812-4334 (shared fax, please use a cover page)

Frank Hutter
University of British Columbia
2366 Main Mall
Vancouver, BC, V6T 1Y4 Canada

778-229-7936 (cell phone)
604-822-6625 (LCI lab)
604-822-5485 (shared fax, please use a cover page)

Program Committee

Collocated events

We would like to inform potential attendees that AAAI-06 will also have a separate related workshop on "heuristic search, memory based heuristics and their applications". That workshop will be held on the following day (July 17) to enable interested people to attend both workshops if they so wish. See the following link for more details.

Workshop on Heuristic Search, Memory Based Heuristics and Their Applications, organised by Ariel Felner, Hector Geffner, and Robert Holte.

Previous meetings on related topics

Related links

Wiki for research on automated parameter tuning (hosted by Tom Carchrae)