Simon Ståhlberg
Principal Research Engineer
About me
I am a principal research engineer at Linköping University, Sweden. My research interest is in the field of artificial intelligence, with a focus on classical planning. Currently, I am researching how neural networks can be used to learn generalized policies so that entire classes of planning instances can be solved.
Short bio
I have done all my studies at Linköping University: I completed my bachelor's and master's degree in computer science in 2010 and 2012, respectively; and I received my PhD in 2017. After my studies, I worked in the industry for a while, and I resumed my research when this lab was founded.
Awards
- ICAPS 2022 Best Paper Award for the paper Learning General Optimal Policies with Graph Neural Networks: Expressive Power, Transparency, and Limits with Blai Bonet and Hector Geffner at the 32th International Conference on Automated Planning and Scheduling (ICAPS 2022).
- IJCAI 2021 Distinguished Paper Award for the paper Learning Generalized Unsolvability Heuristics for Classical Planning (PDF) with Jendrik Seipp and Guillem Francès at the 30th International Joint Conference on Artificial Intelligence (IJCAI 2021).
Publications
2022
Simon Ståhlberg, Blai Bonet and Hector Geffner.
Learning Generalized Policies without Supervision Using GNNs.
In Proceedings of the Nineteenth International Conference on Principles of Knowledge Representation and Reasoning (KR 2022). 2022.
paper slides citationSimon Ståhlberg, Blai Bonet and Hector Geffner.
Learning General Optimal Policies with Graph Neural Networks: Expressive Power, Transparency, and Limits.
In Proceedings of the Thirty-Second International Conference on Automated Planning and Scheduling (ICAPS 2022). 2022.
paper slides citation
2021
Simon Ståhlberg, Guillem Francès and Jendrik Seipp.
Learning Generalized Unsolvability Heuristics for Classical Planning.
In Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI 2021), pp. 4175–4181. 2021.
paper slides poster code citation
2017
Simon Ståhlberg.
Methods for Detecting Unsolvable Planning Instances using Variable Projection.
PhD thesis, Linköping University, 2017.
citationSimon Ståhlberg.
Tailoring Pattern Databases for Unsolvable Planning Instances.
In Proceedings of the Twenty-Seventh International Conference on Automated Planning and Scheduling (ICAPS 2017), pp. 274–282. 2017.
paper citation
2016
Meysam Aghighi, Christer Bäckström, Peter Jonsson and Simon Ståhlberg.
Analysing Approximability and Heuristics in Planning Using the Exponential-Time Hypothesis.
In Proceedings of the 22nd European Conference on Artificial Intelligence (ECAI 2016). 2016.
citationMeysam Aghighi, Christer Bäckström, Peter Jonsson and Simon Ståhlberg.
Refining complexity analyses in planning by exploiting the exponential time hypothesis.
Annals of Mathematics and Artificial Intelligence 78, pp. 157–175. 2016.
citation
2015
Meysam Aghighi, Peter Jonsson and Simon Ståhlberg.
Tractable Cost-Optimal Planning Over Restricted Polytree Causal Graphs.
In Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI 2015), pp. 3225–3231. 2015.
paper citation
2013
Christer Bäckström, Peter Jonsson and Simon Ståhlberg.
Fast Detection of Unsolvable Planning Instances Using Local Consistency.
In Proceedings of the Sixth Annual Symposium on Combinatorial Search (SoCS 2013), pp. 29–37. 2013.
paper citation