Home

Winners Announced

Congratulations to the PbP.s team (Beniamino Galvani; Alfonso E. Gerevini; Alessandro Saetti; Mauro Vallati) for being the overall winner of the competition!

Congratulations to Sungwook Yoon of PARC for winning the best learner award with his entry ObtuseWedge!

Many thanks to all of the teams that participated, making the competition a success!

Description

The International Planning Competition (IPC) has been a bi-annual event. The objectives of the competition are to provide a forum for empirical comparison of planning systems, to highlight challenges to the community in the form of problems at the edge of current capabilities, to propose new directions for research and to provide a core of common benchmark problems and a representation formalism that can aid in the comparison and evaluation of planning systems. Although the series has a competitive style (individual systems are identified for exceptional performance at the event itself), the focus is on data-collection and presentation, with interpretation of results being understated. The real goal of the competition is to make as much data as possible available to the community.

The sixth international planning competition, IPC-6 for short, has been organized in the context of International Conference on Automated Planning and Scheduling (ICAPS). IPC-6 and its organization is split into three parts: the deterministic part, that considers fully deterministic and observable planning (previously also called "classical" planning), the uncertainty part that considers non-deterministic and probabilistic actions in fully observable, partially observable or unobservable domains and the new planning with learning part, where planners exploit domain dependent knowledge that has been automatically extracted during an offline training period.

Previous planning competitions had 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 do 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.