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

Información del proyecto

RLeap

Identificador del acuerdo de subvención: 885107

DOI

10.3030/885107

Proyecto cerrado

Fecha de la firma de la CE 24 Abril 2020

Fecha de inicio 1 Octubre 2020

Fecha de finalización 31 Marzo 2026

Financiado con arreglo a

• EXCELLENT SCIENCE - European Research Council (ERC)

Coste total

€ 2 498 625,00

Aportación de la UE

€ 2 498 625,00

Coordinado por

RHEINISCH-WESTFAELISCHE TECHNISCHE HOCHSCHULE AACHEN
Germany

CORDIS proporciona enlaces a los documentos públicos y las publicaciones de los proyectos de los programas marco HORIZONTE.

Los enlaces a los documentos y las publicaciones de los proyectos del Séptimo Programa Marco, así como los enlaces a algunos tipos de resultados específicos, como conjuntos de datos y «software», se obtienen dinámicamente de OpenAIRE .

Resultado final

Open Research Data Pilot (1)

Data Management Plan (DMP).

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

Publicaciones

Peer reviewed articles (5)

FOND planning with explicit fairness assumptions

Autores: Rodriguez, Ivan D.; Bonet, Blai; Sardina, Sebastian; Geffner, Hector
Publicado en: Journal of Artificial Intelligence Research, Edición 4, 2022, ISSN 1076-9757
Editor: Morgan Kaufmann Publishers, Inc.
DOI: 10.1613/jair.1.13599

Automated planning instance generation with neuro-symbolic AI

Autores: Carlos Núñez-Molina, Pablo Mesejo, Juan Fernández-Olivares
Publicado en: Artificial Intelligence, Edición 352, 2026, Página(s) 104471, ISSN 0004-3702
Editor: Elsevier BV
DOI: 10.1016/j.artint.2025.104471

First-Order Representation Languages for Goal-Conditioned RL

Autores: Simon Ståhlberg, Hector Geffner
Publicado en: Proceedings of the AAAI Conference on Artificial Intelligence, Edición 40, 2026, Página(s) 36394-36402, ISSN 2374-3468
Editor: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/aaai.v40i43.40960

General Policies, Subgoal Structure, and Planning Width

Autores: Blai Bonet, Hector Geffner
Publicado en: Journal of Artificial Intelligence Research, Edición 80, 2024, Página(s) 475-516, ISSN 1076-9757
Editor: Morgan Kaufmann Publishers, Inc.
DOI: 10.1613/jair.1.15581

Expressing and Exploiting Subgoal Structure in Classical Planning Using Sketches

Autores: Dominik Drexler, Jendrik Seipp, Hector Geffner
Publicado en: Journal of Artificial Intelligence Research, Edición 80, 2024, ISSN 1076-9757
Editor: Morgan Kaufmann Publishers, Inc.
DOI: 10.1613/jair.1.15821

Conference proceedings (32)

Learning Generalized Policies Without Supervision Using GNNs

Autores: Simon Stählberg, Blai Bonet, Hector Geffner
Publicado en: Proc. Int. Conf. on Principles of Knowledge Representation and Reasoning (KR), 2022
Editor: IJCAI Organization
DOI: 10.48550/arxiv.2205.06002

General Policies, Serializations, and Planning Width

Autores: Bonet, Blai; Geffner, Hector
Publicado en: Proceedings AAAI, 2021
Editor: AAAI Press

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

Autores: Blai Bonet, Dominik Drexler, Héctor Geffner
Publicado en: Proceedings of the International Conference on Automated Planning and Scheduling, Edición 34, 2024, Página(s) 31-39, ISSN 2334-0843
Editor: AAAI Press
DOI: 10.1609/icaps.v34i1.31458

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

Autores: Dominik Drexler, Jendrik Seipp, Hector Geffner
Publicado en: Proceedings of the 18th International Conference on Principles of Knowledge Representation and Reasoning, 2021
Editor: IJCAI Organization

Learning Generalized Policies for Fully Observable Non-Deterministic Planning Domains

Autores: Hofmann, Till; Geffner, Hector
Publicado en: Proc. Int. Joint Conference on Artificial Intelligence (IJCAI), 2025
Editor: IJCAI Organization
DOI: 10.48550/arxiv.2404.02499

Online Action Recognition

Autores: Suárez Hernández, Alejandro; Segovia Aguas, Javier; Torras, Carme; Alenyà Ribas, Guillem
Publicado en: Proc. National Conf. on Artificial Intelligence (AAAI), 2021
Editor: AAAI Press
DOI: 10.48550/arxiv.2012.07464

Learning first-order symbolic planning representations that are grounded

Autores: Andres Occhipinti, Blai Bonet, Hector Geffner
Publicado en: Proc. ICAPS Workshop on Bridging the Gap Between AI Planning and Reinforcement Learning, 2022
Editor: AAAI Press
DOI: 10.48550/arxiv.2204.11902

Learning General Policies with Policy Gradient Methods

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

Learning Generalized Policies for Fully Observable Non-Deterministic Planning Domains

Autores: Till Hofmann, Hector Geffner
Publicado en: Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence, 2024, ISBN 978-1-956792-04-1
Editor: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/ijcai.2024/744

Learning to Ground Existentially Quantified Goals

Autores: Martin Funkquist, Simon Ståhlberg, Hector Geffner
Publicado en: Proc. Int. Conf. on Knowledge Representation and Reasoning, 2024
Editor: IJCAI Org

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

Autores: Jonas Gösgens, Niklas Jansen, Hector Geffner
Publicado en: Proceedings of the International Conference on Automated Planning and Scheduling, Edición 35, 2025, Página(s) 189-197, ISSN 2334-0843
Editor: 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

Autores: Dominik Drexler, Jendrik Seipp, Hector Geffner
Publicado en: Proc. Int. Conf. on Planning and Scheduling (ICAPS), 2022
Editor: AAAI Press

Learning Generalized Policies for Fully Observable Non-Deterministic Planning Domains

Autores: Till Hofmann, Hector Geffner
Publicado en: Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence, 2025
Editor: IJCAI Organization

Learning General Policies from Small Examples Without Supervision

Autores: Francès, Guillem; Bonet, Blai; Geffner, Hector
Publicado en: Proceedings AAAI, 2021
Editor: AAAI Press
DOI: 10.48550/arxiv.2101.00692

Learning to Search and Searching to Learn for Generalization in Planning

Autores: Michael Aichmüller , Yannik Hesse , Hector Geffner
Publicado en: Proc. Int. Conf. on Machine Learning (ICML), 2026
Editor: Proc. of Machine Learning Research (PMLR)

Learning More Expressive General Policies for Classical Planning Domains

Autores: Simon Ståhlberg, Blai Bonet, Hector Geffner
Publicado en: Proceedings of the AAAI Conference on Artificial Intelligence, Edición 39, 2025, Página(s) 26697-26706
Editor: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/aaai.v39i25.34872

Symmetries and Expressive Requirements for Learning General Policies

Autores: Dominik Drexler, Simon Ståhlberg, Blai Bonet, Hector Geffner
Publicado en: Proc. Int. Conf. on Knowledge Representation and Reasoning, 2024
Editor: IJCAI Org.

Learning Hierarchical Policies by Iteratively Reducing the Width of Sketch Rules

Autores: Dominik Drexler, Jendrik Seipp, Hector Geffner
Publicado en: Proceedings of the Twentieth International Conference on Principles of Knowledge Representation and Reasoning, 2023, Página(s) 208-218
Editor: 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

Autores: Ivan D. Rodriguez; Blai Bonet; Javier Romero; Hector Geffner
Publicado en: Proceedings of the 18th International Conference on Principles of Knowledge Representation and Reasoning, 2021
Editor: IJCAI Organization
DOI: 10.24963/kr.2021/51

Generalized Planning as Heuristic Search

Autores: Segovia-Aguas, Javier; Jiménez, Sergio; Jonsson, Anders
Publicado en: Proc. Int. Conf. on Planning and Scheduling (ICAPS), 2021
Editor: AAAI Press
DOI: 10.48550/arxiv.2103.14434

Learning Lifted Action Models from Traces of Incomplete Actions and States

Autores: Niklas Jansen, Jonas Gösgens, Hector Geffner
Publicado en: Proceedings of the TwentySecond International Conference on Principles of Knowledge Representation and Reasoning, 2025, Página(s) 832-842
Editor: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/kr.2025/80

Symmetries and Expressive Requirements for Learning General Policies

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

Flexible FOND Planning with Explicit Fairness Assumptions

Autores: Rodriguez, Ivan D.; Bonet, Blai; Sardina, Sebastian; Geffner, Hector
Publicado en: Proceedings of the Thirty-First International Conference on Automated Planning and Scheduling, 2021
Editor: AAAI Press

Learning General Policies from Examples

Autores: Blai Bonet, Hector Geffner
Publicado en: Proceedings of the TwentySecond International Conference on Principles of Knowledge Representation and Reasoning, 2025, Página(s) 740-750
Editor: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/kr.2025/71

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

Autores: Geffner, Hector
Publicado en: Proceedings AAAI, 2022
Editor: AAAI Press

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

Autores: Ståhlberg, Simon; Bonet, Blai; Geffner, Hector
Publicado en: Proceedings of the Thirty-Second International Conference on Automated Planning and Scheduling, 2022
Editor: AAAI Press
DOI: 10.48550/arxiv.2109.10129

From Next Token Prediction to (STRIPS) World Models

Autores: Carlos Núñez-Molina, Vicenç Gómez, Hector Geffner
Publicado en: Proc. KR, 2026
Editor: IJCAI Organization

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

Autores: Jonas Gösgens, Niklas Jansen, Hector Geffner
Publicado en: Proc. KR., 2026
Editor: IJCAI Organization

Sketch Decompositions for Classical Planning via Deep Reinforcement Learning

Autores: Michael Aichmüller, Hector Geffner
Publicado en: Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, 2025, Página(s) 8438-8446
Editor: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/ijcai.2025/938

LTLf Synthesis on First-Order Agent Programs in Nondeterministic Environments

Autores: Till Hofmann, Jens Claßen
Publicado en: Proceedings of the AAAI Conference on Artificial Intelligence, Edición 39, 2025, Página(s) 14976-14986
Editor: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/aaai.v39i14.33642

Combined Task and Motion Planning via Sketch Decompositions

Autores: Magí Dalmau Moreno, Néstor García, Vicenç Gómez, Héctor Geffner
Publicado en: Proceedings of the International Conference on Automated Planning and Scheduling, Edición 34, 2024, Página(s) 123-132, ISSN 2334-0843
Editor: AAAI Press
DOI: 10.1609/icaps.v34i1.31468

Learning to Ground Existentially Quantified Goals

Autores: Martin Funkquist, Simon Ståhlberg, Hector Geffner
Publicado en: Proceedings of the TwentyFirst International Conference on Principles of Knowledge Representation and Reasoning, 2024, Página(s) 856-866
Editor: 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

Autores: Hector Geffner, Rina Dechter, Joseph Y. Halpern (Editors)
Publicado en: 2022
Editor: ACM Books
DOI: 10.1145/3501714

Other (2)

Differentiable Learning of Lifted Action Schemas for Classical Planning

Autores: Jonas Reiter, Jakob Elias Gebler, Hector Geffner
Publicado en: Submitted, 2026
Editor: Arxiv

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

Autores: Michael Aichmüller, Simon Ståhlberg, Martin Funkquist, Hector Geffner
Publicado en: Submitted, 2026
Editor: Arxiv