From Data-based to Model-based AI: Representation Learning for Planning

Project Information

RLeap

Grant agreement ID: 885107

DOI

10.3030/885107

Project closed

EC signature date 24 April 2020

Start date 1 October 2020

End date 31 March 2026

Funded under

• EXCELLENT SCIENCE - European Research Council (ERC)

Total cost

€ 2 498 625,00

EU contribution

€ 2 498 625,00

Coordinated by

RHEINISCH-WESTFAELISCHE TECHNISCHE HOCHSCHULE AACHEN
Germany

CORDIS provides links to public deliverables and publications of HORIZON projects.

Links to deliverables and publications from FP7 projects, as well as links to some specific result types such as dataset and software, are dynamically retrieved from OpenAIRE .

Deliverables

Open Research Data Pilot (1)

Data Management Plan (DMP).

The Open Research Data Pilot will be prepared and submitted to the European Commission.

Publications

Peer reviewed articles (5)

FOND planning with explicit fairness assumptions

Author(s): Rodriguez, Ivan D.; Bonet, Blai; Sardina, Sebastian; Geffner, Hector
Published in: Journal of Artificial Intelligence Research, Issue 4, 2022, ISSN 1076-9757
Publisher: Morgan Kaufmann Publishers, Inc.
DOI: 10.1613/jair.1.13599

Automated planning instance generation with neuro-symbolic AI

Author(s): Carlos Núñez-Molina, Pablo Mesejo, Juan Fernández-Olivares
Published in: Artificial Intelligence, Issue 352, 2026, Page(s) 104471, ISSN 0004-3702
Publisher: Elsevier BV
DOI: 10.1016/j.artint.2025.104471

First-Order Representation Languages for Goal-Conditioned RL

Author(s): Simon Ståhlberg, Hector Geffner
Published in: Proceedings of the AAAI Conference on Artificial Intelligence, Issue 40, 2026, Page(s) 36394-36402, ISSN 2374-3468
Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/aaai.v40i43.40960

General Policies, Subgoal Structure, and Planning Width

Author(s): Blai Bonet, Hector Geffner
Published in: Journal of Artificial Intelligence Research, Issue 80, 2024, Page(s) 475-516, ISSN 1076-9757
Publisher: Morgan Kaufmann Publishers, Inc.
DOI: 10.1613/jair.1.15581

Expressing and Exploiting Subgoal Structure in Classical Planning Using Sketches

Author(s): Dominik Drexler, Jendrik Seipp, Hector Geffner
Published in: Journal of Artificial Intelligence Research, Issue 80, 2024, ISSN 1076-9757
Publisher: Morgan Kaufmann Publishers, Inc.
DOI: 10.1613/jair.1.15821

Conference proceedings (32)

Learning Generalized Policies Without Supervision Using GNNs

Author(s): Simon Stählberg, Blai Bonet, Hector Geffner
Published in: Proc. Int. Conf. on Principles of Knowledge Representation and Reasoning (KR), 2022
Publisher: IJCAI Organization
DOI: 10.48550/arxiv.2205.06002

General Policies, Serializations, and Planning Width

Author(s): Bonet, Blai; Geffner, Hector
Published in: Proceedings AAAI, 2021
Publisher: AAAI Press

On Policy Reuse: An Expressive Language for Representing and Executing General Policies that Call Other Policies

Author(s): Blai Bonet, Dominik Drexler, Héctor Geffner
Published in: Proceedings of the International Conference on Automated Planning and Scheduling, Issue 34, 2024, Page(s) 31-39, ISSN 2334-0843
Publisher: AAAI Press
DOI: 10.1609/icaps.v34i1.31458

Expressing and Exploiting the Common Subgoal Structure of Classical Planning Domains Using Sketches.

Author(s): Dominik Drexler, Jendrik Seipp, Hector Geffner
Published in: Proceedings of the 18th International Conference on Principles of Knowledge Representation and Reasoning, 2021
Publisher: IJCAI Organization

Learning Generalized Policies for Fully Observable Non-Deterministic Planning Domains

Author(s): Hofmann, Till; Geffner, Hector
Published in: Proc. Int. Joint Conference on Artificial Intelligence (IJCAI), 2025
Publisher: IJCAI Organization
DOI: 10.48550/arxiv.2404.02499

Online Action Recognition

Author(s): Suárez Hernández, Alejandro; Segovia Aguas, Javier; Torras, Carme; Alenyà Ribas, Guillem
Published in: Proc. National Conf. on Artificial Intelligence (AAAI), 2021
Publisher: AAAI Press
DOI: 10.48550/arxiv.2012.07464

Learning first-order symbolic planning representations that are grounded

Author(s): Andres Occhipinti, Blai Bonet, Hector Geffner
Published in: Proc. ICAPS Workshop on Bridging the Gap Between AI Planning and Reinforcement Learning, 2022
Publisher: AAAI Press
DOI: 10.48550/arxiv.2204.11902

Learning General Policies with Policy Gradient Methods

Author(s): Simon Ståhlberg, Blai Bonet, Hector Geffner
Published in: Proceedings of the Twentieth International Conference on Principles of Knowledge Representation and Reasoning, 2023, Page(s) 647-657, ISBN 978-1-956792-02-7
Publisher: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/kr.2023/63

Learning Generalized Policies for Fully Observable Non-Deterministic Planning Domains

Author(s): Till Hofmann, Hector Geffner
Published in: Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence, 2024, ISBN 978-1-956792-04-1
Publisher: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/ijcai.2024/744

Learning to Ground Existentially Quantified Goals

Author(s): Martin Funkquist, Simon Ståhlberg, Hector Geffner
Published in: Proc. Int. Conf. on Knowledge Representation and Reasoning, 2024
Publisher: IJCAI Org

Learning Lifted STRIPS Models from Action Traces alone: A Simple, General, and Scalable Solution

Author(s): Jonas Gösgens, Niklas Jansen, Hector Geffner
Published in: Proceedings of the International Conference on Automated Planning and Scheduling, Issue 35, 2025, Page(s) 189-197, ISSN 2334-0843
Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/icaps.v35i1.36117

Learning Sketches for Decomposing Planning Problems into Subproblems of Bounded Width

Author(s): Dominik Drexler, Jendrik Seipp, Hector Geffner
Published in: Proc. Int. Conf. on Planning and Scheduling (ICAPS), 2022
Publisher: AAAI Press

Learning Generalized Policies for Fully Observable Non-Deterministic Planning Domains

Author(s): Till Hofmann, Hector Geffner
Published in: Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence, 2025
Publisher: IJCAI Organization

Learning General Policies from Small Examples Without Supervision

Author(s): Francès, Guillem; Bonet, Blai; Geffner, Hector
Published in: Proceedings AAAI, 2021
Publisher: AAAI Press
DOI: 10.48550/arxiv.2101.00692

Learning to Search and Searching to Learn for Generalization in Planning

Author(s): Michael Aichmüller , Yannik Hesse , Hector Geffner
Published in: Proc. Int. Conf. on Machine Learning (ICML), 2026
Publisher: Proc. of Machine Learning Research (PMLR)

Learning More Expressive General Policies for Classical Planning Domains

Author(s): Simon Ståhlberg, Blai Bonet, Hector Geffner
Published in: Proceedings of the AAAI Conference on Artificial Intelligence, Issue 39, 2025, Page(s) 26697-26706
Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/aaai.v39i25.34872

Symmetries and Expressive Requirements for Learning General Policies

Author(s): Dominik Drexler, Simon Ståhlberg, Blai Bonet, Hector Geffner
Published in: Proc. Int. Conf. on Knowledge Representation and Reasoning, 2024
Publisher: IJCAI Org.

Learning Hierarchical Policies by Iteratively Reducing the Width of Sketch Rules

Author(s): Dominik Drexler, Jendrik Seipp, Hector Geffner
Published in: Proceedings of the Twentieth International Conference on Principles of Knowledge Representation and Reasoning, 2023, Page(s) 208-218
Publisher: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/kr.2023/21

Learning First-Order Representations for Planning from Black Box States: New Results

Author(s): Ivan D. Rodriguez; Blai Bonet; Javier Romero; Hector Geffner
Published in: Proceedings of the 18th International Conference on Principles of Knowledge Representation and Reasoning, 2021
Publisher: IJCAI Organization
DOI: 10.24963/kr.2021/51

Generalized Planning as Heuristic Search

Author(s): Segovia-Aguas, Javier; Jiménez, Sergio; Jonsson, Anders
Published in: Proc. Int. Conf. on Planning and Scheduling (ICAPS), 2021
Publisher: AAAI Press
DOI: 10.48550/arxiv.2103.14434

Learning Lifted Action Models from Traces of Incomplete Actions and States

Author(s): Niklas Jansen, Jonas Gösgens, Hector Geffner
Published in: Proceedings of the TwentySecond International Conference on Principles of Knowledge Representation and Reasoning, 2025, Page(s) 832-842
Publisher: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/kr.2025/80

Symmetries and Expressive Requirements for Learning General Policies

Author(s): Dominik Drexler, Simon Ståhlberg, Blai Bonet, Hector Geffner
Published in: Proceedings of the TwentyFirst International Conference on Principles of Knowledge Representation and Reasoning, 2024, Page(s) 845-855
Publisher: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/kr.2024/79

Flexible FOND Planning with Explicit Fairness Assumptions

Author(s): Rodriguez, Ivan D.; Bonet, Blai; Sardina, Sebastian; Geffner, Hector
Published in: Proceedings of the Thirty-First International Conference on Automated Planning and Scheduling, 2021
Publisher: AAAI Press

Learning General Policies from Examples

Author(s): Blai Bonet, Hector Geffner
Published in: Proceedings of the TwentySecond International Conference on Principles of Knowledge Representation and Reasoning, 2025, Page(s) 740-750
Publisher: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/kr.2025/71

Target Languages (vs. Inductive Biases) for Learning to Act and Plan

Author(s): Geffner, Hector
Published in: Proceedings AAAI, 2022
Publisher: AAAI Press

Learning General Optimal Policies with Graph Neural Networks: Expressive Power, Transparency, and Limits

Author(s): Ståhlberg, Simon; Bonet, Blai; Geffner, Hector
Published in: Proceedings of the Thirty-Second International Conference on Automated Planning and Scheduling, 2022
Publisher: AAAI Press
DOI: 10.48550/arxiv.2109.10129

From Next Token Prediction to (STRIPS) World Models

Author(s): Carlos Núñez-Molina, Vicenç Gómez, Hector Geffner
Published in: Proc. KR, 2026
Publisher: IJCAI Organization

Learning Lifted Action Models from Traces with Minimal Information About Actions and States

Author(s): Jonas Gösgens, Niklas Jansen, Hector Geffner
Published in: Proc. KR., 2026
Publisher: IJCAI Organization

Sketch Decompositions for Classical Planning via Deep Reinforcement Learning

Author(s): Michael Aichmüller, Hector Geffner
Published in: Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, 2025, Page(s) 8438-8446
Publisher: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/ijcai.2025/938

LTLf Synthesis on First-Order Agent Programs in Nondeterministic Environments

Author(s): Till Hofmann, Jens Claßen
Published in: Proceedings of the AAAI Conference on Artificial Intelligence, Issue 39, 2025, Page(s) 14976-14986
Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/aaai.v39i14.33642

Combined Task and Motion Planning via Sketch Decompositions

Author(s): Magí Dalmau Moreno, Néstor García, Vicenç Gómez, Héctor Geffner
Published in: Proceedings of the International Conference on Automated Planning and Scheduling, Issue 34, 2024, Page(s) 123-132, ISSN 2334-0843
Publisher: AAAI Press
DOI: 10.1609/icaps.v34i1.31468

Learning to Ground Existentially Quantified Goals

Author(s): Martin Funkquist, Simon Ståhlberg, Hector Geffner
Published in: Proceedings of the TwentyFirst International Conference on Principles of Knowledge Representation and Reasoning, 2024, Page(s) 856-866
Publisher: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/kr.2024/80

Monographic books (1)

Probabilistic and Causal Inference: The Works of Judea Pearl

Author(s): Hector Geffner, Rina Dechter, Joseph Y. Halpern (Editors)
Published in: 2022
Publisher: ACM Books
DOI: 10.1145/3501714

Other (2)

Differentiable Learning of Lifted Action Schemas for Classical Planning

Author(s): Jonas Reiter, Jakob Elias Gebler, Hector Geffner
Published in: Submitted, 2026
Publisher: Arxiv

Efficient Lookahead Encoding and Abstracted Width for Learning General Policies in Classical Planning

Author(s): Michael Aichmüller, Simon Ståhlberg, Martin Funkquist, Hector Geffner
Published in: Submitted, 2026
Publisher: Arxiv