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

Informacje na temat projektu

RLeap

Identyfikator umowy o grant: 885107

DOI

10.3030/885107

Projekt został zamknięty

Data podpisania przez KE 24 Kwietnia 2020

Data rozpoczęcia 1 Października 2020

Data zakończenia 31 Marca 2026

Finansowanie w ramach

• EXCELLENT SCIENCE - European Research Council (ERC)

Koszt całkowity

€ 2 498 625,00

Wkład UE

€ 2 498 625,00

Koordynowany przez

RHEINISCH-WESTFAELISCHE TECHNISCHE HOCHSCHULE AACHEN
Germany

CORDIS oferuje możliwość skorzystania z odnośników do publicznie dostępnych publikacji i rezultatów projektów realizowanych w ramach programów ramowych HORYZONT.

Odnośniki do rezultatów i publikacji związanych z poszczególnymi projektami 7PR, a także odnośniki do niektórych konkretnych kategorii wyników, takich jak zbiory danych i oprogramowanie, są dynamicznie pobierane z systemu OpenAIRE .

Rezultaty

Open Research Data Pilot (1)

Data Management Plan (DMP).

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

Publikacje

Peer reviewed articles (5)

FOND planning with explicit fairness assumptions

Autorzy: Rodriguez, Ivan D.; Bonet, Blai; Sardina, Sebastian; Geffner, Hector
Opublikowane w: Journal of Artificial Intelligence Research, Numer 4, 2022, ISSN 1076-9757
Wydawca: Morgan Kaufmann Publishers, Inc.
DOI: 10.1613/jair.1.13599

Automated planning instance generation with neuro-symbolic AI

Autorzy: Carlos Núñez-Molina, Pablo Mesejo, Juan Fernández-Olivares
Opublikowane w: Artificial Intelligence, Numer 352, 2026, Strona(/y) 104471, ISSN 0004-3702
Wydawca: Elsevier BV
DOI: 10.1016/j.artint.2025.104471

First-Order Representation Languages for Goal-Conditioned RL

Autorzy: Simon Ståhlberg, Hector Geffner
Opublikowane w: Proceedings of the AAAI Conference on Artificial Intelligence, Numer 40, 2026, Strona(/y) 36394-36402, ISSN 2374-3468
Wydawca: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/aaai.v40i43.40960

General Policies, Subgoal Structure, and Planning Width

Autorzy: Blai Bonet, Hector Geffner
Opublikowane w: Journal of Artificial Intelligence Research, Numer 80, 2024, Strona(/y) 475-516, ISSN 1076-9757
Wydawca: Morgan Kaufmann Publishers, Inc.
DOI: 10.1613/jair.1.15581

Expressing and Exploiting Subgoal Structure in Classical Planning Using Sketches

Autorzy: Dominik Drexler, Jendrik Seipp, Hector Geffner
Opublikowane w: Journal of Artificial Intelligence Research, Numer 80, 2024, ISSN 1076-9757
Wydawca: Morgan Kaufmann Publishers, Inc.
DOI: 10.1613/jair.1.15821

Conference proceedings (32)

Learning Generalized Policies Without Supervision Using GNNs

Autorzy: Simon Stählberg, Blai Bonet, Hector Geffner
Opublikowane w: Proc. Int. Conf. on Principles of Knowledge Representation and Reasoning (KR), 2022
Wydawca: IJCAI Organization
DOI: 10.48550/arxiv.2205.06002

General Policies, Serializations, and Planning Width

Autorzy: Bonet, Blai; Geffner, Hector
Opublikowane w: Proceedings AAAI, 2021
Wydawca: AAAI Press

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

Autorzy: Blai Bonet, Dominik Drexler, Héctor Geffner
Opublikowane w: Proceedings of the International Conference on Automated Planning and Scheduling, Numer 34, 2024, Strona(/y) 31-39, ISSN 2334-0843
Wydawca: AAAI Press
DOI: 10.1609/icaps.v34i1.31458

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

Autorzy: Dominik Drexler, Jendrik Seipp, Hector Geffner
Opublikowane w: Proceedings of the 18th International Conference on Principles of Knowledge Representation and Reasoning, 2021
Wydawca: IJCAI Organization

Learning Generalized Policies for Fully Observable Non-Deterministic Planning Domains

Autorzy: Hofmann, Till; Geffner, Hector
Opublikowane w: Proc. Int. Joint Conference on Artificial Intelligence (IJCAI), 2025
Wydawca: IJCAI Organization
DOI: 10.48550/arxiv.2404.02499

Online Action Recognition

Autorzy: Suárez Hernández, Alejandro; Segovia Aguas, Javier; Torras, Carme; Alenyà Ribas, Guillem
Opublikowane w: Proc. National Conf. on Artificial Intelligence (AAAI), 2021
Wydawca: AAAI Press
DOI: 10.48550/arxiv.2012.07464

Learning first-order symbolic planning representations that are grounded

Autorzy: Andres Occhipinti, Blai Bonet, Hector Geffner
Opublikowane w: Proc. ICAPS Workshop on Bridging the Gap Between AI Planning and Reinforcement Learning, 2022
Wydawca: AAAI Press
DOI: 10.48550/arxiv.2204.11902

Learning General Policies with Policy Gradient Methods

Autorzy: Simon Ståhlberg, Blai Bonet, Hector Geffner
Opublikowane w: Proceedings of the Twentieth International Conference on Principles of Knowledge Representation and Reasoning, 2023, Strona(/y) 647-657, ISBN 978-1-956792-02-7
Wydawca: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/kr.2023/63

Learning Generalized Policies for Fully Observable Non-Deterministic Planning Domains

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

Learning to Ground Existentially Quantified Goals

Autorzy: Martin Funkquist, Simon Ståhlberg, Hector Geffner
Opublikowane w: Proc. Int. Conf. on Knowledge Representation and Reasoning, 2024
Wydawca: IJCAI Org

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

Autorzy: Jonas Gösgens, Niklas Jansen, Hector Geffner
Opublikowane w: Proceedings of the International Conference on Automated Planning and Scheduling, Numer 35, 2025, Strona(/y) 189-197, ISSN 2334-0843
Wydawca: 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

Autorzy: Dominik Drexler, Jendrik Seipp, Hector Geffner
Opublikowane w: Proc. Int. Conf. on Planning and Scheduling (ICAPS), 2022
Wydawca: AAAI Press

Learning Generalized Policies for Fully Observable Non-Deterministic Planning Domains

Autorzy: Till Hofmann, Hector Geffner
Opublikowane w: Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence, 2025
Wydawca: IJCAI Organization

Learning General Policies from Small Examples Without Supervision

Autorzy: Francès, Guillem; Bonet, Blai; Geffner, Hector
Opublikowane w: Proceedings AAAI, 2021
Wydawca: AAAI Press
DOI: 10.48550/arxiv.2101.00692

Learning to Search and Searching to Learn for Generalization in Planning

Autorzy: Michael Aichmüller , Yannik Hesse , Hector Geffner
Opublikowane w: Proc. Int. Conf. on Machine Learning (ICML), 2026
Wydawca: Proc. of Machine Learning Research (PMLR)

Learning More Expressive General Policies for Classical Planning Domains

Autorzy: Simon Ståhlberg, Blai Bonet, Hector Geffner
Opublikowane w: Proceedings of the AAAI Conference on Artificial Intelligence, Numer 39, 2025, Strona(/y) 26697-26706
Wydawca: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/aaai.v39i25.34872

Symmetries and Expressive Requirements for Learning General Policies

Autorzy: Dominik Drexler, Simon Ståhlberg, Blai Bonet, Hector Geffner
Opublikowane w: Proc. Int. Conf. on Knowledge Representation and Reasoning, 2024
Wydawca: IJCAI Org.

Learning Hierarchical Policies by Iteratively Reducing the Width of Sketch Rules

Autorzy: Dominik Drexler, Jendrik Seipp, Hector Geffner
Opublikowane w: Proceedings of the Twentieth International Conference on Principles of Knowledge Representation and Reasoning, 2023, Strona(/y) 208-218
Wydawca: 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

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

Generalized Planning as Heuristic Search

Autorzy: Segovia-Aguas, Javier; Jiménez, Sergio; Jonsson, Anders
Opublikowane w: Proc. Int. Conf. on Planning and Scheduling (ICAPS), 2021
Wydawca: AAAI Press
DOI: 10.48550/arxiv.2103.14434

Learning Lifted Action Models from Traces of Incomplete Actions and States

Autorzy: Niklas Jansen, Jonas Gösgens, Hector Geffner
Opublikowane w: Proceedings of the TwentySecond International Conference on Principles of Knowledge Representation and Reasoning, 2025, Strona(/y) 832-842
Wydawca: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/kr.2025/80

Symmetries and Expressive Requirements for Learning General Policies

Autorzy: Dominik Drexler, Simon Ståhlberg, Blai Bonet, Hector Geffner
Opublikowane w: Proceedings of the TwentyFirst International Conference on Principles of Knowledge Representation and Reasoning, 2024, Strona(/y) 845-855
Wydawca: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/kr.2024/79

Flexible FOND Planning with Explicit Fairness Assumptions

Autorzy: Rodriguez, Ivan D.; Bonet, Blai; Sardina, Sebastian; Geffner, Hector
Opublikowane w: Proceedings of the Thirty-First International Conference on Automated Planning and Scheduling, 2021
Wydawca: AAAI Press

Learning General Policies from Examples

Autorzy: Blai Bonet, Hector Geffner
Opublikowane w: Proceedings of the TwentySecond International Conference on Principles of Knowledge Representation and Reasoning, 2025, Strona(/y) 740-750
Wydawca: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/kr.2025/71

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

Autorzy: Geffner, Hector
Opublikowane w: Proceedings AAAI, 2022
Wydawca: AAAI Press

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

Autorzy: Ståhlberg, Simon; Bonet, Blai; Geffner, Hector
Opublikowane w: Proceedings of the Thirty-Second International Conference on Automated Planning and Scheduling, 2022
Wydawca: AAAI Press
DOI: 10.48550/arxiv.2109.10129

From Next Token Prediction to (STRIPS) World Models

Autorzy: Carlos Núñez-Molina, Vicenç Gómez, Hector Geffner
Opublikowane w: Proc. KR, 2026
Wydawca: IJCAI Organization

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

Autorzy: Jonas Gösgens, Niklas Jansen, Hector Geffner
Opublikowane w: Proc. KR., 2026
Wydawca: IJCAI Organization

Sketch Decompositions for Classical Planning via Deep Reinforcement Learning

Autorzy: Michael Aichmüller, Hector Geffner
Opublikowane w: Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, 2025, Strona(/y) 8438-8446
Wydawca: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/ijcai.2025/938

LTLf Synthesis on First-Order Agent Programs in Nondeterministic Environments

Autorzy: Till Hofmann, Jens Claßen
Opublikowane w: Proceedings of the AAAI Conference on Artificial Intelligence, Numer 39, 2025, Strona(/y) 14976-14986
Wydawca: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/aaai.v39i14.33642

Combined Task and Motion Planning via Sketch Decompositions

Autorzy: Magí Dalmau Moreno, Néstor García, Vicenç Gómez, Héctor Geffner
Opublikowane w: Proceedings of the International Conference on Automated Planning and Scheduling, Numer 34, 2024, Strona(/y) 123-132, ISSN 2334-0843
Wydawca: AAAI Press
DOI: 10.1609/icaps.v34i1.31468

Learning to Ground Existentially Quantified Goals

Autorzy: Martin Funkquist, Simon Ståhlberg, Hector Geffner
Opublikowane w: Proceedings of the TwentyFirst International Conference on Principles of Knowledge Representation and Reasoning, 2024, Strona(/y) 856-866
Wydawca: 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

Autorzy: Hector Geffner, Rina Dechter, Joseph Y. Halpern (Editors)
Opublikowane w: 2022
Wydawca: ACM Books
DOI: 10.1145/3501714

Other (2)

Differentiable Learning of Lifted Action Schemas for Classical Planning

Autorzy: Jonas Reiter, Jakob Elias Gebler, Hector Geffner
Opublikowane w: Submitted, 2026
Wydawca: Arxiv

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

Autorzy: Michael Aichmüller, Simon Ståhlberg, Martin Funkquist, Hector Geffner
Opublikowane w: Submitted, 2026
Wydawca: Arxiv