Initial state prediction in planning

Senka Krivic, Michael Cashmore, Bram Ridder, Daniele Magazzeni, Sandor Szedmak, Justus Piater

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

1 Downloads (Pure)

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 multi- graph utilizing Maximum-Margin Multi-Valued Regression. We evaluate this approach in four different domains, demonstrating high recall and accuracy.
Original languageEnglish
Title of host publicationThe AAAI-17 Workshop on Knowledge-Based Techniques for Problem Solving and Reasoning - Technical Report
Place of PublicationMenlo Park, US-CA.
Number of pages8
VolumeWS-17-12
Publication statusPublished - 5 Feb 2017

Keywords

  • planning
  • initial state prediction

Fingerprint Dive into the research topics of 'Initial state prediction in planning'. Together they form a unique fingerprint.

  • Cite this

    Krivic, S., Cashmore, M., Ridder, B., Magazzeni, D., Szedmak, S., & Piater, J. (2017). Initial state prediction in planning. In The AAAI-17 Workshop on Knowledge-Based Techniques for Problem Solving and Reasoning - Technical Report (Vol. WS-17-12). Menlo Park, US-CA..