Initial State Prediction in Planning

Senka Krivic, Michael Cashmore, Bram Ridder, Daniele Magazzeni, Sándor Szedmák, Justus H. Piater

Abstract: While recent advances in offline reasoning techniques and online execution strategies have made planning under uncertainty more robust, the application of plans in partially-known environments is still a difficult and important topic. In this paper we present an approach for predicting new information about a partially-known initial state, represented as a multigraph utilizing Maximum-Margin Multi-Valued Regression. We evaluate this approach in four different domains, demonstrating high recall and accuracy.