Hector Geffner
Guest Professor
Short bio
Hector Geffner got his Ph.D at UCLA in 1989. He then worked as Staff Research Member at the IBM T.J. Watson Research Center in NY, USA and at the Universidad Simon Bolivar, in Caracas, Venezuela. Since 2001 and until December 2022, he was a researcher at ICREA and a professor at the Universitat Pompeu Fabra, Barcelona. Hector is a former Associate Editor of Artificial Intelligence and the Journal of Artificial Intelligence Research, and a Fellow of AAAI and EurAI. He is the author of the book Default Reasoning: Causal and Conditional Theories, MIT Press, 1992, and "A Concise Introduction to Models and Methods for Automated Planning" with Blai Bonet, Morgan and Claypool, 2013. He edited two books with Rina Dechter and Joe Halpern: "Heuristics, Probability, and Causality: a Tribute to Judea Pearl", College Publications, 2010, and Probabilistic and Causal Inference: The Works of Judea Pearl, ACM Books 2022. Hector is interested in computational models of reasoning, action, learning, and planning that are general and effective. He is also a concerned citizen (particularly concerned these days) and aside from courses on logic and AI, he teaches a course on social and technological change. Hector leads a project on representation learning for acting and planning, funded by an Advanced ERC grant, 2020-2025. Since January 2023, Hector is an Alexander von Humboldt Professor at the Computer Science Department of RWTH Aachen University where he heads the Chair of Machine Learning and Reasoning. He is also a Guest Wallenberg Professor at Linköping University.
Below you find the list of papers published together with colleges from the Machine Reasoning Lab. For more papers, see here.
Awards
- ICAPS 2022 Best Paper Award for the paper Learning General Optimal Policies with Graph Neural Networks: Expressive Power, Transparency, and Limits with Simon Ståhlberg and Blai Bonet at the 32nd International Conference on Automated Planning and Scheduling (ICAPS 2022).
Publications
2024
Dominik Drexler, Simon Ståhlberg, Blai Bonet and Hector Geffner.
Symmetries and Expressive Requirements for Learning General Policies.
In Proceedings of the Twenty-First International Conference on Principles of Knowledge Representation and Reasoning (KR 2024). 2024.
paper citationMartin Funkquist, Simon Ståhlberg and Hector Geffner.
Learning to Ground Existentially Quantified Goals.
In Proceedings of the Twenty-First International Conference on Principles of Knowledge Representation and Reasoning (KR 2024). 2024.
paper code citationBlai Bonet, Dominik Drexler and Hector Geffner.
On Policy Reuse: An Expressive Language for Representing and Executing General Policies that Call Other Policies.
In Proceedings of the Thirty-Fourth International Conference on Automated Planning and Scheduling (ICAPS 2024), pp. 31–39. 2024.
paper slides citationDominik Drexler, Simon Ståhlberg, Blai Bonet and Hector Geffner.
Equivalence-Based Abstractions for Learning General Policies.
In ICAPS 2024 Workshop on Bridging the Gap Between AI Planning and Reinforcement Learning (PRL). 2024.
paper slides citationDominik Drexler, Jendrik Seipp and Hector Geffner.
Expressing and Exploiting Subgoal Structure in Classical Planning Using Sketches.
Journal of Artificial Intelligence Research 80, pp. 171–208. 2024.
paper citation
2023
Blai Bonet, Dominik Drexler and Hector Geffner.
General and Reusable Indexical Policies and Sketches.
In NeurIPS 2023 Workshop on Generalization in Planning. 2023.
paper code citationSimon Ståhlberg, Blai Bonet and Hector Geffner.
Learning General Policies with Policy Gradient Methods.
In Proceedings of the Twentieth International Conference on Principles of Knowledge Representation and Reasoning (KR 2023), pp. 647–657. 2023.
paper citationDominik Drexler, Jendrik Seipp and Hector Geffner.
Learning Hierarchical Policies by Iteratively Reducing the Width of Sketch Rules.
In Proceedings of the Twentieth International Conference on Principles of Knowledge Representation and Reasoning (KR 2023), pp. 208–218. 2023.
paper slides code citation
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), pp. 474–483. 2022.
paper slides code 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), pp. 629–637. 2022.
paper slides citationDominik Drexler, Jendrik Seipp and Hector Geffner.
Learning Sketches for Decomposing Planning Problems into Subproblems of Bounded Width.
In Proceedings of the Thirty-Second International Conference on Automated Planning and Scheduling (ICAPS 2022), pp. 62–70. 2022.
paper slides poster code citation
2021
Dominik Drexler, Jendrik Seipp and Hector Geffner.
Expressing and Exploiting the Common Subgoal Structure of Classical Planning Domains Using Sketches.
In Proceedings of the Eighteenth International Conference on Principles of Knowledge Representation and Reasoning (KR 2021), pp. 258–268. 2021.
paper slides recording poster citation