Jendrik Seipp
Assistant Professor
About me
I am assistant professor in Artificial Intelligence at Linköping University, Sweden. Together with Hector Geffner, I lead the "Representation, Learning and Planning" lab in the AIICS division. My main research interests are automated planning and its connections to machine learning.
Short bio
I received my MSc in computer science from the University of Freiburg, Germany, in December 2012. In March 2018, I completed my PhD under the supervision of Prof. Malte Helmert with the Artificial Intelligence group at the University of Basel, Switzerland. Afterwards, I stayed on as a postdoc until I became assistant professor at Linköping University, Sweden, in January 2021.
For more information, please see my academic CV.
Software
- Planning system: Fast Downward
- Optimal classical planner: Scorpion
- Experiment framework: Downward Lab
Tutorials
- ICAPS 2020 tutorial "Evaluating Planners with Downward Lab"
- ICAPS 2015 tutorial "Latest Trends in Abstraction Heuristics for Classical Planning" (with Malte Helmert and Silvan Sievers)
Awards
- 4x First Place, 3x Second Place, 1x Third Place (in nine tracks) at the First CoRe Challenge for the system PARIS: Planning Algorithms for Reconfiguring Independent Sets with Remo Christen, Salomé Eriksson, Michael Katz, Emil Keyder, Christian Muise, Alice Petrov, Florian Pommerening, Silvan Sievers, and David Speck at the ICALP 2022 Workshop on Combinatorial Reconfiguration, Paris.
- Second Place, System Demonstrations Track for the system Planutils: Bringing Planning to the Masses with Christian Muise, Florian Pommerening, and Michael Katz 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 with Simon Ståhlberg and Guillem Francès at the 30th International Joint Conference on Artificial Intelligence (IJCAI 2021).
- ICAPS 2020 Best Dissertation Award for the doctoral thesis Counterexample-guided Cartesian Abstraction Refinement and Saturated Cost Partitioning for Optimal Classical Planning at the 30th International Conference on Automated Planning and Scheduling (ICAPS 2020).
- SoCS 2020 Best Paper Award for the paper An Atom-Centric Perspective on Stubborn Sets with Gabriele Röger, Malte Helmert, and Silvan Sievers at the 13th International Symposium on Combinatorial Search (SoCS 2020).
- Winner, Deterministic Sequential Satisficing Track for the planning system Fast Downward Stone Soup 2018 with Gabriele Röger at the 9th International Planning Competition (IPC 2018) at ICAPS 2018.
- Winner, Deterministic Sequential Cost-Bounded Track for the planning system Fast Downward Stone Soup 2018 with Gabriele Röger at the 9th International Planning Competition (IPC 2018) at ICAPS 2018.
- SoCS 2017 Best Student Paper Award for the paper Better Orders for Saturated Cost Partitioning in Optimal Classical Planning at the 10th Annual Symposium on Combinatorial Search (SoCS 2017).
- Winner, Unsolvability IPC 2016 for the planning system Fast Downward Aidos with Florian Pommerening, Silvan Sievers, Martin Wehrle, Chris Fawcett, and Yusra Alkhazraji at the 1st Unsolvability International Planning Competition (UIPC 2016) at ICAPS 2016.
- AAAI 2015 Outstanding Paper Award for the paper From Non-Negative to General Operator Cost Partitioning with Florian Pommerening, Malte Helmert, and Gabriele Röger at the 29th AAAI Conference on Artificial Intelligence (AAAI 2015).
- Runner-Up and "Best Learner" Award, Learning Track for the planning system Fast Downward Cedalion with Silvan Sievers and Frank Hutter at the 8th International Planning Competition (IPC 2014) at ICAPS 2014.
- Third Place and "Best Basic Solver" Award, Learning Track for the planning system Fast Downward SMAC with Silvan Sievers and Frank Hutter at the 8th International Planning Competition (IPC 2014) at ICAPS 2014.
- Winner, Deterministic Sequential Optimization Track for the planning system Fast Downward Stone Soup-1 with Malte Helmert, Gabriele Röger, Erez Karpas, Jörg Hoffmann, Emil Keyder, Raz Nissim, Silvia Richter, and Matthias Westphal at the 7th International Planning Competition (IPC 2011) at ICAPS 2011.
- Runner-Up, Deterministic Sequential Satisficing Track for the planning system Fast Downward Stone Soup with Malte Helmert, Gabriele Röger, Erez Karpas, Jörg Hoffmann, Emil Keyder, Raz Nissim, Silvia Richter, and Matthias Westphal at the 7th International Planning Competition (IPC 2011) at ICAPS 2011.
- Runner-Up, Learning Track for the planning system Fast Downward Autotune-speed with Chris Fawcett, Malte Helmert, Holger Hoos, Erez Karpas, and Gabriele Röger at the 7th International Planning Competition (IPC 2011) at ICAPS 2011.
Publications
2022
Patrick Ferber, Liat Cohen, Jendrik Seipp and Thomas Keller.
Learning and Exploiting Progress States in Greedy Best-First Search.
In Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI 2022), pp. 4740–4746. 2022.
paper slides poster code citationDominik Drexler, Javier Segovia-Aguas and Jendrik Seipp.
Learning General Policies and Helpful Action Classifiers from Partial State Spaces.
In IJCAI 2022 Workshop on Generalization in Planning. 2022.
paper slides citationRemo Christen, Salomé Eriksson, Michael Katz, Emil Keyder, Christian Muise, Alice Petrov, Florian Pommerening, Jendrik Seipp, Silvan Sievers and David Speck.
(PARIS) Planning Algorithms for Reconfiguring Independent Sets.
In First CoRe Challenge: Solver and Graph Descriptions, pp. 15–22. 2022.
paper citationAugusto B. Corrêa and Jendrik Seipp.
Best-First Width Search for Lifted Classical Planning.
In Proceedings of the Thirty-Second International Conference on Automated Planning and Scheduling (ICAPS 2022), pp. 11–15. 2022.
paper slides poster code 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 citationDavid Speck and Jendrik Seipp.
New Refinement Strategies for Cartesian Abstractions.
In Proceedings of the Thirty-Second International Conference on Automated Planning and Scheduling (ICAPS 2022), pp. 348–352. 2022.
paper slides recording poster code citationChristian Muise, Florian Pommerening, Jendrik Seipp and Michael Katz.
Planutils: Bringing Planning to the Masses.
In 32nd International Conference on Automated Planning and Scheduling, System Demonstrations and Exhibits. 2022.
paper recording poster citationClemens Büchner, Patrick Ferber, Jendrik Seipp and Malte Helmert.
A Comparison of Abstraction Heuristics for Rubik's Cube.
In ICAPS 2022 Workshop on Heuristics and Search for Domain-independent Planning (HSDIP). 2022.
paper slides recording code citationAndré Biedenkapp, David Speck, Silvan Sievers, Frank Hutter, Marius Lindauer and Jendrik Seipp.
Learning Domain-Independent Policies for Open List Selection.
In ICAPS 2022 Workshop on Bridging the Gap Between AI Planning and Reinforcement Learning (PRL). 2022.
paper slides recording citationPatrick Ferber and Jendrik Seipp.
Explainable Planner Selection for Classical Planning.
In Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI 2022), pp. 9741–9749. 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 citationSimon 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 citationDominik Drexler, Jendrik Seipp and David Speck.
Subset-Saturated Transition Cost Partitioning.
In Proceedings of the Thirty-First International Conference on Automated Planning and Scheduling (ICAPS 2021), pp. 131–139. 2021.
paper slides poster code citationFlorian Pommerening, Thomas Keller, Valentina Halasi, Jendrik Seipp, Silvan Sievers and Malte Helmert.
Dantzig-Wolfe Decomposition for Cost Partitioning.
In Proceedings of the Thirty-First International Conference on Automated Planning and Scheduling (ICAPS 2021), pp. 271–280. 2021.
paper technical report slides recording poster code citationJendrik Seipp.
Online Saturated Cost Partitioning for Classical Planning.
In Proceedings of the Thirty-First International Conference on Automated Planning and Scheduling (ICAPS 2021), pp. 317–321. 2021.
paper slides poster code citationÁlvaro Torralba, Jendrik Seipp and Silvan Sievers.
Automatic Instance Generation for Classical Planning.
In Proceedings of the Thirty-First International Conference on Automated Planning and Scheduling (ICAPS 2021), pp. 376–384. 2021.
paper slides poster code citationJendrik Seipp, Thomas Keller and Malte Helmert.
Saturated Post-hoc Optimization for Classical Planning.
In Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI 2021), pp. 11947–11953. 2021.
paper slides recording poster code citation
2020
Jendrik Seipp, Samuel von Allmen and Malte Helmert.
Incremental Search for Counterexample-Guided Cartesian Abstraction Refinement.
In Proceedings of the Thirtieth International Conference on Automated Planning and Scheduling (ICAPS 2020), pp. 244–248. 2020.
paper slides recording poster code citationJendrik Seipp.
Online Saturated Cost Partitioning for Classical Planning.
In ICAPS 2020 Workshop on Heuristics and Search for Domain-independent Planning (HSDIP), pp. 16–22. 2020.
paper slides recording code citation (Superseded by the ICAPS 2021 paper with the same name.)Patrick Ferber and Jendrik Seipp.
Explainable Planner Selection.
In ICAPS 2020 Workshop on Explainable AI Planning (XAIP). 2020.
paper slides recording poster citation (Superseded by the AAAI 2022 paper "Explainable Planner Selection for Classical Planning".)Álvaro Torralba, Jendrik Seipp and Silvan Sievers.
Automatic Configuration of Benchmark Sets for Classical Planning.
In ICAPS 2020 Workshop on Heuristics and Search for Domain-independent Planning (HSDIP), pp. 58–66. 2020.
paper slides recording citation (Superseded by the ICAPS 2021 paper "Automatic Instance Generation for Classical Planning".)Gabriele Röger, Malte Helmert, Jendrik Seipp and Silvan Sievers.
An Atom-Centric Perspective on Stubborn Sets.
In Proceedings of the 13th Annual Symposium on Combinatorial Search (SoCS 2020), pp. 57–65. 2020.
paper slides recording code citationJendrik Seipp, Thomas Keller and Malte Helmert.
Saturated Cost Partitioning for Optimal Classical Planning.
Journal of Artificial Intelligence Research 67, pp. 129–167. 2020.
paper code citation
2019
Jendrik Seipp.
Pattern Selection for Optimal Classical Planning with Saturated Cost Partitioning.
In Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI 2019), pp. 5621–5627. 2019.
paper slides code citationJendrik Seipp and Malte Helmert.
Subset-Saturated Cost Partitioning for Optimal Classical Planning.
In Proceedings of the Twenty-Ninth International Conference on Automated Planning and Scheduling (ICAPS 2019), pp. 391–400. 2019.
paper technical report slides code citationJendrik Seipp.
Planner Metrics Should Satisfy Independence of Irrelevant Alternatives.
In ICAPS 2019 Workshop on the International Planning Competition (WIPC), pp. 40–41. 2019.
paper slides citationJendrik Seipp.
Pattern Selection for Optimal Classical Planning with Saturated Cost Partitioning.
In ICAPS 2019 Workshop on Heuristics and Search for Domain-independent Planning (HSDIP), pp. 72–80. 2019.
paper slides citation (Superseded by the IJCAI 2019 paper with the same name.)
2018
Jendrik Seipp and Malte Helmert.
Counterexample-Guided Cartesian Abstraction Refinement for Classical Planning.
Journal of Artificial Intelligence Research 62, pp. 535–577. 2018.
paper citationJendrik Seipp.
Fast Downward Remix.
In Ninth International Planning Competition (IPC-9): Planner Abstracts, pp. 74–76. 2018.
paper citationJendrik Seipp.
Fast Downward Scorpion.
In Ninth International Planning Competition (IPC-9): Planner Abstracts, pp. 77–79. 2018.
paper citationJendrik Seipp and Gabriele Röger.
Fast Downward Stone Soup 2018.
In Ninth International Planning Competition (IPC-9): Planner Abstracts, pp. 80–82. 2018.
paper citationJendrik Seipp.
Counterexample-guided Cartesian Abstraction Refinement and Saturated Cost Partitioning for Optimal Classical Planning.
PhD thesis, University of Basel, 2018.
paper slides recording citation
2017
Jendrik Seipp, Thomas Keller and Malte Helmert.
A Comparison of Cost Partitioning Algorithms for Optimal Classical Planning.
In Proceedings of the Twenty-Seventh International Conference on Automated Planning and Scheduling (ICAPS 2017), pp. 259–268. 2017.
paper slides recording poster citationJendrik Seipp.
Better Orders for Saturated Cost Partitioning in Optimal Classical Planning.
In Proceedings of the 10th Annual Symposium on Combinatorial Search (SoCS 2017), pp. 149–153. 2017.
paper slides citationJendrik Seipp, Thomas Keller and Malte Helmert.
Narrowing the Gap Between Saturated and Optimal Cost Partitioning for Classical Planning.
In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI 2017), pp. 3651–3657. 2017.
paper slides citation
2016
Thomas Keller, Florian Pommerening, Jendrik Seipp, Florian Geißer and Robert Mattmüller.
State-dependent Cost Partitionings for Cartesian Abstractions in Classical Planning.
In Proceedings of the 25th International Joint Conference on Artificial Intelligence (IJCAI 2016), pp. 3161–3169. 2016.
paper technical report citationJendrik Seipp, Florian Pommerening, Gabriele Röger and Malte Helmert.
Correlation Complexity of Classical Planning Domains.
In Proceedings of the 25th International Joint Conference on Artificial Intelligence (IJCAI 2016), pp. 3242–3250. 2016.
paper slides poster citationFlorian Pommerening and Jendrik Seipp.
Fast Downward Dead-End Pattern Database.
In Unsolvability International Planning Competition: Planner Abstracts, pp. 2. 2016.
paper citationJendrik Seipp, Florian Pommerening, Silvan Sievers, Martin Wehrle, Chris Fawcett and Yusra Alkhazraji.
Fast Downward Aidos.
In Unsolvability International Planning Competition: Planner Abstracts, pp. 28–38. 2016.
paper code citationJendrik Seipp, Florian Pommerening, Gabriele Röger and Malte Helmert.
Correlation Complexity of Classical Planning Domains.
In ICAPS 2016 Workshop on Heuristics and Search for Domain-independent Planning (HSDIP), pp. 12–20. 2016.
paper slides citation (Superseded by the IJCAI 2016 paper with the same name.)
2015
Jendrik Seipp, Florian Pommerening and Malte Helmert.
New Optimization Functions for Potential Heuristics.
In Proceedings of the Twenty-Fifth International Conference on Automated Planning and Scheduling (ICAPS 2015), pp. 193–201. 2015.
paper slides recording citationJendrik Seipp, Silvan Sievers, Malte Helmert and Frank Hutter.
Automatic Configuration of Sequential Planning Portfolios.
In Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI 2015), pp. 3364–3370. 2015.
paper technical report slides code data citationFlorian Pommerening, Malte Helmert, Gabriele Röger and Jendrik Seipp.
From Non-Negative to General Operator Cost Partitioning.
In Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI 2015), pp. 3335–3341. 2015.
paper technical report erratum slides citation
2014
Jendrik Seipp, Silvan Sievers and Frank Hutter.
Fast Downward SMAC.
In Eighth International Planning Competition (IPC-8) Planning and Learning Part: Planner Abstracts. 2014.
paper code citationJendrik Seipp, Silvan Sievers and Frank Hutter.
Fast Downward Cedalion.
In Eighth International Planning Competition (IPC-8) Planning and Learning Part: Planner Abstracts. 2014.
paper code citationJendrik Seipp, Silvan Sievers and Frank Hutter.
Fast Downward Cedalion.
In Eighth International Planning Competition (IPC-8): Planner Abstracts, pp. 17–27. 2014.
paper code citationJendrik Seipp, Manuel Braun and Johannes Garimort.
Fast Downward Uniform Portfolio.
In Eighth International Planning Competition (IPC-8): Planner Abstracts, pp. 32. 2014.
paper citationGabriele Röger, Florian Pommerening and Jendrik Seipp.
Fast Downward Stone Soup 2014.
In Eighth International Planning Competition (IPC-8): Planner Abstracts, pp. 28–31. 2014.
paper citationJendrik Seipp and Malte Helmert.
Diverse and Additive Cartesian Abstraction Heuristics.
In Proceedings of the Twenty-Fourth International Conference on Automated Planning and Scheduling (ICAPS 2014), pp. 289–297. 2014.
paper slides recording citation
2013
Jendrik Seipp and Malte Helmert.
Additive Counterexample-guided Cartesian Abstraction Refinement.
In Late-Breaking Developments in the Field of Artificial Intelligence – Papers Presented at the Twenty-Seventh AAAI Conference on Artificial Intelligence (AAAI 2013) – AAAI Technical Report WS-13-17, pp. 119–121. 2013.
paper citationJendrik Seipp and Malte Helmert.
Counterexample-guided Cartesian Abstraction Refinement.
In Proceedings of the Twenty-Third International Conference on Automated Planning and Scheduling (ICAPS 2013), pp. 347–351. 2013.
paper slides recording citation
2012
Jendrik Seipp.
Counterexample-guided Abstraction Refinement for Classical Planning.
Master's thesis, University of Freiburg, 2012.
paper citationJendrik Seipp, Manuel Braun, Johannes Garimort and Malte Helmert.
Learning Portfolios of Automatically Tuned Planners.
In Proceedings of the Twenty-Second International Conference on Automated Planning and Scheduling (ICAPS 2012), pp. 368–372. 2012.
paper technical report slides code citation (This version of the paper fixes a small mistake in the published version. In Section "Tuning Planners", the published version states that preferred operators are used in 20 of the 21 configurations. The correct statement is that they are used in 19 of the 21 configurations.)
2011
Carmel Domshlak, Malte Helmert, Erez Karpas, Emil Keyder, Silvia Richter, Gabriele Röger, Jendrik Seipp and Matthias Westphal.
BJOLP: The Big Joint Optimal Landmarks Planner.
In IPC 2011 Planner Abstracts, pp. 91–95. 2011.
paper citationChris Fawcett, Malte Helmert, Holger Hoos, Erez Karpas, Gabriele Röger and Jendrik Seipp.
FD-Autotune: Automated Configuration of Fast Downward.
In IPC 2011 Planner Abstracts, pp. 31–37. 2011.
paper citationChris Fawcett, Malte Helmert, Holger Hoos, Erez Karpas, Gabriele Röger and Jendrik Seipp.
FD-Autotune: Domain-Specific Configuration of Fast Downward.
In IPC 2011 Planner Abstracts, Planning and Learning Part. 2011.
paper citationMalte Helmert, Gabriele Röger, Jendrik Seipp, Erez Karpas, Jörg Hoffmann, Emil Keyder, Raz Nissim, Silvia Richter and Matthias Westphal.
Fast Downward Stone Soup.
In IPC 2011 Planner Abstracts, pp. 38–45. 2011.
paper citationChris Fawcett, Malte Helmert, Holger Hoos, Erez Karpas, Gabriele Röger and Jendrik Seipp.
FD-Autotune: Domain-Specific Configuration using Fast Downward.
In ICAPS 2011 Workshop on Planning and Learning, pp. 13–17. 2011.
paper citationJendrik Seipp and Malte Helmert.
Fluent Merging for Classical Planning Problems.
In ICAPS 2011 Workshop on Knowledge Engineering for Planning and Scheduling, pp. 47–53. 2011.
paper slides code citation (This version of the paper fixes two mistakes (in Def. 2 and in the text after Def. 3) that are present in the version of the paper that is linked from the workshop webpage.)
2009
Jendrik Seipp.
Fluent Merging für klassische Planungsprobleme.
Bachelor's thesis, University of Freiburg, 2009.
paper citation (In German.)