Data-Driven Verification and Learning Under Uncertainty

Información del proyecto

DEUCE

Identificador del acuerdo de subvención: 101077178

DOI

10.3030/101077178

Fecha de la firma de la CE 6 Diciembre 2022

Fecha de inicio 1 Enero 2023

Fecha de finalización 31 Diciembre 2027

Financiado con arreglo a

• European Research Council (ERC)

Coste total

€ 1 500 000,00

Aportación de la UE

€ 1 500 000,00

Coordinado por

RUHR-UNIVERSITAET BOCHUM
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 .

Publicaciones

Peer reviewed articles (4)

Decision-making under uncertainty: beyond probabilities

Autores: Thom Badings, Thiago D. Simão, Marnix Suilen, Nils Jansen
Publicado en: International Journal on Software Tools for Technology Transfer, Edición 25, 2023, ISSN 1433-2779
Editor: Springer Science and Business Media LLC
DOI: 10.1007/S10009-023-00704-3

Strong Simple Policies for POMDPs

Autores: Leonore Winterer, Ralf Wimmer, Bernd Becker, Nils Jansen
Publicado en: International Journal on Software Tools for Technology Transfer, Edición 26, 2024, ISSN 1433-2779
Editor: Springer Science and Business Media LLC
DOI: 10.1007/S10009-024-00747-0

Robust Control for Dynamical Systems with Non-Gaussian Noise via Formal Abstractions

Autores: Thom Badings, Licio Romao, Alessandro Abate, David Parker, Hasan A. Poonawala, Marielle Stoelinga, Nils Jansen
Publicado en: Journal of Artificial Intelligence Research, Edición 76, 2023, ISSN 1076-9757
Editor: AI Access Foundation
DOI: 10.1613/JAIR.1.14253

Parameter synthesis for Markov models: covering the parameter space

Autores: Sebastian Junges, Erika Ábrahám, Christian Hensel, Nils Jansen, Joost-Pieter Katoen, Tim Quatmann, Matthias Volk
Publicado en: Formal Methods in System Design, Edición 62, 2024, ISSN 0925-9856
Editor: Springer Science and Business Media LLC
DOI: 10.1007/S10703-023-00442-X

Conference proceedings (17)

Act-Then-Measure: Reinforcement Learning for Partially Observable Environments with Active Measuring

Autores: Merlijn Krale, Thiago D. Simão, Nils Jansen
Publicado en: Proceedings of the International Conference on Automated Planning and Scheduling, Edición 33, 2023, ISSN 2334-0843
Editor: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/ICAPS.V33I1.27197

Factored Online Planning in Many-Agent POMDPs

Autores: Maris F.L. Galesloot, Thiago D. Simão, Sebastian Junges, Nils Jansen
Publicado en: Proceedings of the AAAI Conference on Artificial Intelligence, Edición 38, 2024, ISSN 2374-3468
Editor: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/AAAI.V38I16.29689

Efficient Sensitivity Analysis for Parametric Robust Markov Chains

Autores: Thom Badings, Sebastian Junges, Ahmadreza Marandi, Ufuk Topcu, Nils Jansen
Publicado en: Lecture Notes in Computer Science, Computer Aided Verification, 2024
Editor: Springer Nature Switzerland
DOI: 10.1007/978-3-031-37709-9_4

A Stability-Based Abstraction Framework for Reach-Avoid Control of Stochastic Dynamical Systems with Unknown Noise Distributions

Autores: Thom Badings, Licio Romao, Alessandro Abate, Nils Jansen
Publicado en: 2024 European Control Conference (ECC), 2024
Editor: IEEE
DOI: 10.23919/ECC64448.2024.10590865

Reinforcement Learning by Guided Safe Exploration

Autores: Qisong Yang, Thiago D. Simão, Nils Jansen, Simon H. Tindemans, Matthijs T. J. Spaan
Publicado en: Frontiers in Artificial Intelligence and Applications, ECAI 2023, 2023
Editor: IOS Press
DOI: 10.3233/FAIA230598

Approximate Dec-POMDP Solving Using Multi-Agent A*

Autores: Wietze Koops, Sebastian Junges, Nils Jansen
Publicado en: Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence, 2024
Editor: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/ijcai.2024/745

Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation

Autores: Yannick Hogewind, Thiago D. Simão, Tal Kachman, Nils Jansen
Publicado en: The Eleventh International Conference on Learning Representations, {ICLR} 2023, 2023
Editor: OpenReview.net

Probabilities Are Not Enough: Formal Controller Synthesis for Stochastic Dynamical Models with Epistemic Uncertainty

Autores: Thom Badings, Licio Romao, Alessandro Abate, Nils Jansen
Publicado en: Proceedings of the AAAI Conference on Artificial Intelligence, Edición 37, 2023, ISSN 2374-3468
Editor: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/AAAI.V37I12.26718

Risk-aware Curriculum Generation for Heavy-tailed Task Distributions

Autores: Koprulu, C.; Simão, T.D.; Jansen, N.; Topcu, U.
Publicado en: Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence, 2023
Editor: Proceedings of Machine Learning Research

Safe Reinforcement Learning via Shielding under Partial Observability

Autores: Steven Carr, Nils Jansen, Sebastian Junges, Ufuk Topcu
Publicado en: Proceedings of the AAAI Conference on Artificial Intelligence, Edición 37, 2023, ISSN 2374-3468
Editor: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/AAAI.V37I12.26723

CTMCs with Imprecisely Timed Observations

Autores: Thom Badings, Matthias Volk, Sebastian Junges, Marielle Stoelinga, Nils Jansen
Publicado en: Lecture Notes in Computer Science, Tools and Algorithms for the Construction and Analysis of Systems, 2024
Editor: Springer Nature Switzerland
DOI: 10.1007/978-3-031-57249-4_13

Robust Active Measuring under Model Uncertainty

Autores: Merlijn Krale, Thiago D. Simão, Jana Tumova, Nils Jansen
Publicado en: Proceedings of the AAAI Conference on Artificial Intelligence, Edición 38, 2024, ISSN 2374-3468
Editor: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/AAAI.V38I19.30122

More for Less: Safe Policy Improvement with Stronger Performance Guarantees

Autores: Patrick Wienhöft, Marnix Suilen, Thiago D. Simão, Clemens Dubslaff, Christel Baier, Nils Jansen
Publicado en: Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 2023
Editor: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/IJCAI.2023/490

Safe Policy Improvement for POMDPs via Finite-State Controllers

Autores: Thiago D. Simão, Marnix Suilen, Nils Jansen
Publicado en: Proceedings of the AAAI Conference on Artificial Intelligence, Edición 37, 2023, ISSN 2374-3468
Editor: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/AAAI.V37I12.26763

A Supervised Learning Approach to Robust Reinforcement Learning for Job Shop Scheduling

Autores: Christoph Schmidl, Thiago Simão, Nils Jansen
Publicado en: Proceedings of the 16th International Conference on Agents and Artificial Intelligence, 2024
Editor: SCITEPRESS - Science and Technology Publications
DOI: 10.5220/0012473600003636

Imprecise Probabilities Meet Partial Observability: Game Semantics for Robust POMDPs

Autores: Eline M. Bovy, Marnix Suilen, Sebastian Junges, Nils Jansen
Publicado en: Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence, 2024
Editor: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/ijcai.2024/740

Recursive Small-Step Multi-Agent A* for Dec-POMDPs

Autores: Wietze Koops, Nils Jansen, Sebastian Junges, Thiago D. Simão
Publicado en: Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 2023
Editor: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/IJCAI.2023/600

Book chapters (1)

Robust Markov Decision Processes: A Place Where AI and Formal Methods Meet

Autores: Marnix Suilen, Thom Badings, Eline M. Bovy, David Parker, Nils Jansen
Publicado en: Lecture Notes in Computer Science, Principles of Verification: Cycling the Probabilistic Landscape, 2024
Editor: Springer Nature Switzerland
DOI: 10.1007/978-3-031-75778-5_7