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

Informations projet

RLeap

N° de convention de subvention: 885107

DOI

10.3030/885107

Projet clôturé

Date de signature de la CE 24 Avril 2020

Date de début 1 Octobre 2020

Date de fin 31 Mars 2026

Financé au titre de

• EXCELLENT SCIENCE - European Research Council (ERC)

Coût total

€ 2 498 625,00

Contribution de l’UE

€ 2 498 625,00

Coordonné par

RHEINISCH-WESTFAELISCHE TECHNISCHE HOCHSCHULE AACHEN
Germany

CORDIS fournit des liens vers les livrables publics et les publications des projets HORIZON.

Les liens vers les livrables et les publications des projets du 7e PC, ainsi que les liens vers certains types de résultats spécifiques tels que les jeux de données et les logiciels, sont récupérés dynamiquement sur OpenAIRE .

Livrables

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

Auteurs: Rodriguez, Ivan D.; Bonet, Blai; Sardina, Sebastian; Geffner, Hector
Publié dans: Journal of Artificial Intelligence Research, Numéro 4, 2022, ISSN 1076-9757
Éditeur: Morgan Kaufmann Publishers, Inc.
DOI: 10.1613/jair.1.13599

Automated planning instance generation with neuro-symbolic AI

Auteurs: Carlos Núñez-Molina, Pablo Mesejo, Juan Fernández-Olivares
Publié dans: Artificial Intelligence, Numéro 352, 2026, Page(s) 104471, ISSN 0004-3702
Éditeur: Elsevier BV
DOI: 10.1016/j.artint.2025.104471

First-Order Representation Languages for Goal-Conditioned RL

Auteurs: Simon Ståhlberg, Hector Geffner
Publié dans: Proceedings of the AAAI Conference on Artificial Intelligence, Numéro 40, 2026, Page(s) 36394-36402, ISSN 2374-3468
Éditeur: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/aaai.v40i43.40960

General Policies, Subgoal Structure, and Planning Width

Auteurs: Blai Bonet, Hector Geffner
Publié dans: Journal of Artificial Intelligence Research, Numéro 80, 2024, Page(s) 475-516, ISSN 1076-9757
Éditeur: Morgan Kaufmann Publishers, Inc.
DOI: 10.1613/jair.1.15581

Expressing and Exploiting Subgoal Structure in Classical Planning Using Sketches

Auteurs: Dominik Drexler, Jendrik Seipp, Hector Geffner
Publié dans: Journal of Artificial Intelligence Research, Numéro 80, 2024, ISSN 1076-9757
Éditeur: Morgan Kaufmann Publishers, Inc.
DOI: 10.1613/jair.1.15821

Conference proceedings (32)

Learning Generalized Policies Without Supervision Using GNNs

Auteurs: Simon Stählberg, Blai Bonet, Hector Geffner
Publié dans: Proc. Int. Conf. on Principles of Knowledge Representation and Reasoning (KR), 2022
Éditeur: IJCAI Organization
DOI: 10.48550/arxiv.2205.06002

General Policies, Serializations, and Planning Width

Auteurs: Bonet, Blai; Geffner, Hector
Publié dans: Proceedings AAAI, 2021
Éditeur: AAAI Press

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

Auteurs: Blai Bonet, Dominik Drexler, Héctor Geffner
Publié dans: Proceedings of the International Conference on Automated Planning and Scheduling, Numéro 34, 2024, Page(s) 31-39, ISSN 2334-0843
Éditeur: AAAI Press
DOI: 10.1609/icaps.v34i1.31458

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

Auteurs: Dominik Drexler, Jendrik Seipp, Hector Geffner
Publié dans: Proceedings of the 18th International Conference on Principles of Knowledge Representation and Reasoning, 2021
Éditeur: IJCAI Organization

Learning Generalized Policies for Fully Observable Non-Deterministic Planning Domains

Auteurs: Hofmann, Till; Geffner, Hector
Publié dans: Proc. Int. Joint Conference on Artificial Intelligence (IJCAI), 2025
Éditeur: IJCAI Organization
DOI: 10.48550/arxiv.2404.02499

Online Action Recognition

Auteurs: Suárez Hernández, Alejandro; Segovia Aguas, Javier; Torras, Carme; Alenyà Ribas, Guillem
Publié dans: Proc. National Conf. on Artificial Intelligence (AAAI), 2021
Éditeur: AAAI Press
DOI: 10.48550/arxiv.2012.07464

Learning first-order symbolic planning representations that are grounded

Auteurs: Andres Occhipinti, Blai Bonet, Hector Geffner
Publié dans: Proc. ICAPS Workshop on Bridging the Gap Between AI Planning and Reinforcement Learning, 2022
Éditeur: AAAI Press
DOI: 10.48550/arxiv.2204.11902

Learning General Policies with Policy Gradient Methods

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

Learning Generalized Policies for Fully Observable Non-Deterministic Planning Domains

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

Learning to Ground Existentially Quantified Goals

Auteurs: Martin Funkquist, Simon Ståhlberg, Hector Geffner
Publié dans: Proc. Int. Conf. on Knowledge Representation and Reasoning, 2024
Éditeur: IJCAI Org

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

Auteurs: Jonas Gösgens, Niklas Jansen, Hector Geffner
Publié dans: Proceedings of the International Conference on Automated Planning and Scheduling, Numéro 35, 2025, Page(s) 189-197, ISSN 2334-0843
Éditeur: 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

Auteurs: Dominik Drexler, Jendrik Seipp, Hector Geffner
Publié dans: Proc. Int. Conf. on Planning and Scheduling (ICAPS), 2022
Éditeur: AAAI Press

Learning Generalized Policies for Fully Observable Non-Deterministic Planning Domains

Auteurs: Till Hofmann, Hector Geffner
Publié dans: Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence, 2025
Éditeur: IJCAI Organization

Learning General Policies from Small Examples Without Supervision

Auteurs: Francès, Guillem; Bonet, Blai; Geffner, Hector
Publié dans: Proceedings AAAI, 2021
Éditeur: AAAI Press
DOI: 10.48550/arxiv.2101.00692

Learning to Search and Searching to Learn for Generalization in Planning

Auteurs: Michael Aichmüller , Yannik Hesse , Hector Geffner
Publié dans: Proc. Int. Conf. on Machine Learning (ICML), 2026
Éditeur: Proc. of Machine Learning Research (PMLR)

Learning More Expressive General Policies for Classical Planning Domains

Auteurs: Simon Ståhlberg, Blai Bonet, Hector Geffner
Publié dans: Proceedings of the AAAI Conference on Artificial Intelligence, Numéro 39, 2025, Page(s) 26697-26706
Éditeur: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/aaai.v39i25.34872

Symmetries and Expressive Requirements for Learning General Policies

Auteurs: Dominik Drexler, Simon Ståhlberg, Blai Bonet, Hector Geffner
Publié dans: Proc. Int. Conf. on Knowledge Representation and Reasoning, 2024
Éditeur: IJCAI Org.

Learning Hierarchical Policies by Iteratively Reducing the Width of Sketch Rules

Auteurs: Dominik Drexler, Jendrik Seipp, Hector Geffner
Publié dans: Proceedings of the Twentieth International Conference on Principles of Knowledge Representation and Reasoning, 2023, Page(s) 208-218
Éditeur: 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

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

Generalized Planning as Heuristic Search

Auteurs: Segovia-Aguas, Javier; Jiménez, Sergio; Jonsson, Anders
Publié dans: Proc. Int. Conf. on Planning and Scheduling (ICAPS), 2021
Éditeur: AAAI Press
DOI: 10.48550/arxiv.2103.14434

Learning Lifted Action Models from Traces of Incomplete Actions and States

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

Symmetries and Expressive Requirements for Learning General Policies

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

Flexible FOND Planning with Explicit Fairness Assumptions

Auteurs: Rodriguez, Ivan D.; Bonet, Blai; Sardina, Sebastian; Geffner, Hector
Publié dans: Proceedings of the Thirty-First International Conference on Automated Planning and Scheduling, 2021
Éditeur: AAAI Press

Learning General Policies from Examples

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

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

Auteurs: Geffner, Hector
Publié dans: Proceedings AAAI, 2022
Éditeur: AAAI Press

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

Auteurs: Ståhlberg, Simon; Bonet, Blai; Geffner, Hector
Publié dans: Proceedings of the Thirty-Second International Conference on Automated Planning and Scheduling, 2022
Éditeur: AAAI Press
DOI: 10.48550/arxiv.2109.10129

From Next Token Prediction to (STRIPS) World Models

Auteurs: Carlos Núñez-Molina, Vicenç Gómez, Hector Geffner
Publié dans: Proc. KR, 2026
Éditeur: IJCAI Organization

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

Auteurs: Jonas Gösgens, Niklas Jansen, Hector Geffner
Publié dans: Proc. KR., 2026
Éditeur: IJCAI Organization

Sketch Decompositions for Classical Planning via Deep Reinforcement Learning

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

LTLf Synthesis on First-Order Agent Programs in Nondeterministic Environments

Auteurs: Till Hofmann, Jens Claßen
Publié dans: Proceedings of the AAAI Conference on Artificial Intelligence, Numéro 39, 2025, Page(s) 14976-14986
Éditeur: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/aaai.v39i14.33642

Combined Task and Motion Planning via Sketch Decompositions

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

Learning to Ground Existentially Quantified Goals

Auteurs: Martin Funkquist, Simon Ståhlberg, Hector Geffner
Publié dans: Proceedings of the TwentyFirst International Conference on Principles of Knowledge Representation and Reasoning, 2024, Page(s) 856-866
Éditeur: 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

Auteurs: Hector Geffner, Rina Dechter, Joseph Y. Halpern (Editors)
Publié dans: 2022
Éditeur: ACM Books
DOI: 10.1145/3501714

Other (2)

Differentiable Learning of Lifted Action Schemas for Classical Planning

Auteurs: Jonas Reiter, Jakob Elias Gebler, Hector Geffner
Publié dans: Submitted, 2026
Éditeur: Arxiv

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

Auteurs: Michael Aichmüller, Simon Ståhlberg, Martin Funkquist, Hector Geffner
Publié dans: Submitted, 2026
Éditeur: Arxiv