2008 International Planning Competition

Learning Track

Call For Participation

The International Planning Competition (IPC) is a biennial event organized in the context of the International Conference on Automated Planning and Scheduling (ICAPS). This year we are pleased to introduce a new learning track of the competition to complement the existing deterministic and probabilistic tracks.

Previous planning competitions have all been structured around a number of planning domains such as Logistics, Freecell, and Airport, with each planner being asked to solve a sequence of problems from each domain. Previous (non-learning) planners in the competitions did not attempt to leverage this structure, for example, by trying to learn from previous problems in a domain to solve future problems in the domain more effectively. The motivation for the learning track is to encourage work on planning systems that do have such learning capabilities.

The general structure of the learning track will be as follows. The competitors will provide two programs to the organizers before the competition begins: a learner and a planner. The competition will then be run in two stages. First, there will be a learning stage, where the learning programs will be provided with the domain definition and example problems for each domain that will appear in the competition. For each domain, the learning program will be given a certain amount of learning time, after which it must output a domain-specific control-knowledge file. Second, there will be an evaluation stage, where, for each domain, the planner will be provided with the appropriate domain-specific control-knowledge file and asked to solve a sequence of test problems from that domain.

The organizers are not placing any constraints on what style of learning approach might be used. For example, a system might utilize statistical/inductive learning or purely deductive learning techniques. In addition, the learning track provides a good venue for entering approaches that might not traditionally be views as learning, such as pure domain-analysis. For example, domain analysis could be conducted during the learning period and the resulting knowledge used during the evaluation period. Ultimately, we hope to see a wide variety of approaches, that will help answer the following questions. How can a planner best use a learning, or domain analysis, period in order to improve future performance?

The learning track will run in the first half of 2008 and will conclude together with ICAPS, in September 2008, in Sydney. It will be organized by Alan Fern, Prasad Tadepalli, and Roni Khardon. Currently we plan to focus on deterministic domains expressed using a subset of the planning domain description language PDDL. The exact PDDL features that will be supported depends largely on initial participant feedback. Depending on interest we may also consider running a probabilistic learning track.

All competitors must submit a 4-page paper describing their planners. A booklet with the papers (possibly electronic) will be distributed among the ICAPS-08 participants.

Finally, an important requirement for IPC-6 competitors is to give the organizers the right to post the code of their planners on the official IPC-6 web site.


Registration and Schedule

Potential participants are requested to send email to afern@eecs.orst.edu expressing interest and providing information on the Participant Interest Form on the web-site. Early expression of interest will provide the opportunity to help shape the structure of the competition.

The final registration deadline is February 29, 2008. Each participant should register by sending an email to afern@eecs.orst.edu including the filled in registration form available from the competition web site.

The tentative schedule of the competition activities are as follows:
Possible additional (intermediate) deadlines will be communicated to the registered participants by the organizers.

We are looking forward to an exciting competition!

The organizers,

Alan Fern, Prasad Tadepalli, Roni Khardon

School of Electrical Engineering and Computer Science, 1148 Kelley Engineering Center
Oregon State University, Corvallis, OR 97331-5501
Send a comment about this web site | This page was last modified on Thursday, December 27, 2007
Copyright © 2008 | Disclaimer | Committed to Diversity