Long, D. and Fox, M. (2006) The International planning competition series and empirical evaluation of AI planning systems. In: Proceedings of Workshop on Empirical Methods for the Analysis of Algorithm, 2006-09-09, Reykjavik, Iceland.
In this paper we consider the role of the International Planning Competition series in the evaluation of planners, both directly through the events themselves, and indirectly through the creation of resources and infrastructure. We also consider the problem of evaluation based on data collected both in the competitions and otherwise and examine some of the issues that arise in attempting to formulate and test hypotheses around the data.
Actions (login required)