Project Publications

• Learning Lifted STRIPS Models from Action Traces Alone: A Simple, General, and Scalable Solution J. Gösgens, N. Jansen, H. Geffner. Proc. 35th International Conference on Automated Planning and Scheduling (ICAPS), 2025.

• Learning More Expressive General Policies for Classical Planning Domains S. Ståhlberg, B. Bonet, H. Geffner. Proc. 39th AAAI Conference on Artificial Intelligence (AAAI), 2025.

• Learning Sketch Decompositions in Planning via Deep Reinforcement Learning M. Aichmüller, H. Geffner. Proc. 34th International Joint Conference on Artificial Intelligence (IJCAI), 2025.

• Learning to Ground Existentially Quantified Goals M. Funkquist, S. Ståhlberg, H. Geffner. Proc. 21st International Conference on Principles of Knowledge Representation and Reasoning (KR), 2024.

• Symmetries and Expressive Requirements for Learning General Policies D. Drexler, S. Ståhlberg, B. Bonet, H. Geffner. Proc. 21st International Conference on Principles of Knowledge Representation and Reasoning (KR), 2024.

• General Policies, Subgoal Structure, and Planning Width B. Bonet, H. Geffner. Journal of Artificial Intelligence Research (JAIR), 2024.

• Expressing and Exploiting Subgoal Structure in Classical Planning Using Sketches D. Drexler, J. Seipp, H. Geffner. Journal of Artificial Intelligence Research (JAIR), 2024.

• On Policy Reuse: A Language for Representing and Executing Nested Policies B. Bonet, D. Drexler, H. Geffner. Proc. 34th International Conference on Automated Planning and Scheduling (ICAPS), 2024.

• Combined Task and Motion Planning Via Sketch Decompositions M. D. Moreno, N. García, V. Gómez, H. Geffner. Proc. 34th International Conference on Automated Planning and Scheduling (ICAPS), 2024.

• Learning Generalized Policies for Fully Observable Non-Deterministic Planning Domains T. Hofmann, H. Geffner. Proc. 34th International Joint Conference on Artificial Intelligence (IJCAI), 2024.

• Equivalence-Based Abstractions for Learning General Policies D. Drexler, S. Ståhlberg, B. Bonet, H. Geffner. Proc. ICAPS Workshop on Planning and Reinforcement Learning (PRL), 2024.

• General and Reusable Indexical Policies and Sketches B. Bonet, D. Drexler, H. Geffner. Proc. NeurIPS Workshop on Generalization in Planning (GenPlan), 2023.

• Learning Hierarchical Policies by Iteratively Reducing the Width of Sketch Rules D. Drexler, J. Seipp, H. Geffner. Proc. 21st International Conference on Principles of Knowledge Representation and Reasoning (KR), 2023.

• Learning Generalized Policies with Policy Gradient Methods S. Ståhlberg, B. Bonet, H. Geffner. Proc. 21st International Conference on Principles of Knowledge Representation and Reasoning (KR), 2023.

• Combined Task and Motion Planning Via Sketch Decompositions M. Dalmau-Moreno, N. Garcia, V. Gomez, H. Geffner. Proc. ICAPS Workshop on Planning and Robotics (PlanRob), 2023.

• Learning Generalized Policies Without Supervision Using GNNs S. Ståhlberg, B. Bonet, H. Geffner. Proc. 21st International Conference on Principles of Knowledge Representation and Reasoning (KR), 2022.

• Learning First-Order Symbolic Planning Representations That Are Grounded A. Occhipinti, B. Bonet, H. Geffner. Proc. ICAPS Workshop on Planning and Reinforcement Learning (PRL), 2022.

• Target Languages (vs. Inductive Biases) for Learning to Act and Plan H. Geffner. Proc. 36th AAAI Conference on Artificial Intelligence (AAAI), 2022. (Slides)

• Learning Sketches for Decomposing Planning Problems into Subproblems of Bounded Width D. Drexler, J. Seipp, H. Geffner. Proc. 32nd International Conference on Automated Planning and Scheduling (ICAPS), 2022.

• Learning General Optimal Policies with Graph Neural Networks S. Ståhlberg, B. Bonet, H. Geffner. Proc. 32nd International Conference on Automated Planning and Scheduling (ICAPS), 2022.

• Learning First-Order Representations for Planning from Black-Box States: New Results. Iván D. Rodriguez, Blai Bonet, Javier Romero, Hector Geffner. Proc. 18th International Conference on Principles of Knowledge Representation and Reasoning (KR), 2021.

• Expressing and Exploiting the Common Subgoal Structure of Classical Planning Domains Using Sketches. Dominik Drexler, Jendrik Seipp, and Hector Geffner. Proc. 18th International Conference on Principles of Knowledge Representation and Reasoning (KR), 2021.

• Learning Generalized Unsolvability Heuristics for Classical Planning. Simon Ståhlberg, Guillem Francès, Jendrik Seipp. Proc. 30th International Joint Conference on Artificial Intelligence (IJCAI), 2021, p.2703-2710.

• Flexible FOND Planning with Explicit Fairness Assumptions. Iván D. Rodriguez, Blai Bonet, Sebastián Sardiña, Hector Geffner. Proc. 31st International Conference on Automated Planning and Scheduling (ICAPS), 2021, p.290-298.

• General Policies, Representations, and Planning Width. Blai Bonet and Hector Geffner. Proc. 35th AAAI Conf. on Artificial Intelligence (AAAI), 2021, p.11764-11773.

• Learning General Planning Policies from Small Examples Without Supervision. Guillem Francès, Blai Bonet, and Hector Geffner. Proc. 35th AAAI Conf. on Artificial Intelligence (AAAI), 2021, p.11801-11808.

• Qualitative Numeric Planning: Reductions and Complexity. Blai Bonet and Hector Geffner. Journal of Artificial Intelligence Research (JAIR), 2020, vol. 69, p.923-961.

• Learning First-Order Symbolic Representations for Planning from the Structure of the State Space. Blai Bonet and Hector Geffner. Proc. 24th European Conf. on Artificial Intelligence (ECAI), 2020.

• Learning Features and Abstract Actions for Computing Generalized Plans. Blai Bonet, Guillem Francès, and Hector Geffner. Proc. 33rd AAAI Conf. on Artificial Intelligence (AAAI), 2019, p.2703-2710.