Photo of Simon Ståhlberg

Simon Ståhlberg

Principal Research Engineer

Researcher within artificial intelligence with a focus on combining automated planning and deep learning.

Artificial intelligence, in the area of classical planning

I am a researcher within artificial intelligence with a focus on combining automated planning and deep learning.

My research interests are in the field of artificial intelligence, specifically in the area of classical planning. I am currently investigating the use of neural networks to learn generalized policies, in order to solve a wide range of planning problems. My focus is on how deep learning can be used to improve traditional planning systems, which are not able to learn from experience or examples, and thus do not scale well to large problems.

CV in brief

Education

I pursued my education at Linköping University, where I completed my Bachelor's and Master's degrees in Computer Science in 2010 and 2012, respectively, and I received my PhD in 2017.

Employment

After completing my studies, I worked in the industry for a while before returning to research as a postdoc when this lab was founded.

Awards

My work in this lab has been recognized by several notable awards in the field of artificial intelligence, including:



Publications

2023

Simon Ståhlberg (2023) Lifted Successor Generation by Maximum Clique Enumeration ECAI 2023
Simon Ståhlberg, Blai Bonet, Hector Geffner (2023) Learning General Policies with Policy Gradient Methods Proceedings of the 20th International Conference on Principles of Knowledge Representation and Reasoning, p. 647-657 Continue to DOI

2022

Simon Ståhlberg, Blai Bonet, Hector Geffner (2022) Learning Generalized Policies without Supervision Using GNNs Proceedings of the 19th International Conference on Principles of Knowledge Representation and Reasoning: Special Session on KR and Machine Learning, p. 474-483 Continue to DOI
Simon Ståhlberg, Blai Bonet, Hector Geffner (2022) Learning General Optimal Policies with Graph Neural Networks: Expressive Power, Transparency, and Limits Proceedings of the Thirty-Second International Conference on Automated Planning and Scheduling (ICAPS 2022), p. 629-637 Continue to DOI

2021

Simon Ståhlberg, Guillem Francès, Jendrik Seipp (2021) Learning Generalized Unsolvability Heuristics for Classical Planning 30th International Joint Conference on Artificial Intelligence, p. 4175-4181

About the division

Colleagues at AIICS

About the department