Data-Driven Verification and Learning Under Uncertainty

Project Information

DEUCE

Grant agreement ID: 101077178

DOI

10.3030/101077178

EC signature date 6 December 2022

Start date 1 January 2023

End date 31 December 2027

Funded under

• European Research Council (ERC)

Total cost

€ 1 500 000,00

EU contribution

€ 1 500 000,00

Coordinated by

RUHR-UNIVERSITAET BOCHUM
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 .

Publications

Peer reviewed articles (4)

Decision-making under uncertainty: beyond probabilities

Author(s): Thom Badings, Thiago D. Simão, Marnix Suilen, Nils Jansen
Published in: International Journal on Software Tools for Technology Transfer, Issue 25, 2023, ISSN 1433-2779
Publisher: Springer Science and Business Media LLC
DOI: 10.1007/S10009-023-00704-3

Strong Simple Policies for POMDPs

Author(s): Leonore Winterer, Ralf Wimmer, Bernd Becker, Nils Jansen
Published in: International Journal on Software Tools for Technology Transfer, Issue 26, 2024, ISSN 1433-2779
Publisher: 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

Author(s): Thom Badings, Licio Romao, Alessandro Abate, David Parker, Hasan A. Poonawala, Marielle Stoelinga, Nils Jansen
Published in: Journal of Artificial Intelligence Research, Issue 76, 2023, ISSN 1076-9757
Publisher: AI Access Foundation
DOI: 10.1613/JAIR.1.14253

Parameter synthesis for Markov models: covering the parameter space

Author(s): Sebastian Junges, Erika Ábrahám, Christian Hensel, Nils Jansen, Joost-Pieter Katoen, Tim Quatmann, Matthias Volk
Published in: Formal Methods in System Design, Issue 62, 2024, ISSN 0925-9856
Publisher: 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

Author(s): Merlijn Krale, Thiago D. Simão, Nils Jansen
Published in: Proceedings of the International Conference on Automated Planning and Scheduling, Issue 33, 2023, ISSN 2334-0843
Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/ICAPS.V33I1.27197

Factored Online Planning in Many-Agent POMDPs

Author(s): Maris F.L. Galesloot, Thiago D. Simão, Sebastian Junges, Nils Jansen
Published in: Proceedings of the AAAI Conference on Artificial Intelligence, Issue 38, 2024, ISSN 2374-3468
Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/AAAI.V38I16.29689

Efficient Sensitivity Analysis for Parametric Robust Markov Chains

Author(s): Thom Badings, Sebastian Junges, Ahmadreza Marandi, Ufuk Topcu, Nils Jansen
Published in: Lecture Notes in Computer Science, Computer Aided Verification, 2024
Publisher: 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

Author(s): Thom Badings, Licio Romao, Alessandro Abate, Nils Jansen
Published in: 2024 European Control Conference (ECC), 2024
Publisher: IEEE
DOI: 10.23919/ECC64448.2024.10590865

Reinforcement Learning by Guided Safe Exploration

Author(s): Qisong Yang, Thiago D. Simão, Nils Jansen, Simon H. Tindemans, Matthijs T. J. Spaan
Published in: Frontiers in Artificial Intelligence and Applications, ECAI 2023, 2023
Publisher: IOS Press
DOI: 10.3233/FAIA230598

Approximate Dec-POMDP Solving Using Multi-Agent A*

Author(s): Wietze Koops, Sebastian Junges, Nils Jansen
Published in: Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence, 2024
Publisher: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/ijcai.2024/745

Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation

Author(s): Yannick Hogewind, Thiago D. Simão, Tal Kachman, Nils Jansen
Published in: The Eleventh International Conference on Learning Representations, {ICLR} 2023, 2023
Publisher: OpenReview.net

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

Author(s): Thom Badings, Licio Romao, Alessandro Abate, Nils Jansen
Published in: Proceedings of the AAAI Conference on Artificial Intelligence, Issue 37, 2023, ISSN 2374-3468
Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/AAAI.V37I12.26718

Risk-aware Curriculum Generation for Heavy-tailed Task Distributions

Author(s): Koprulu, C.; Simão, T.D.; Jansen, N.; Topcu, U.
Published in: Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence, 2023
Publisher: Proceedings of Machine Learning Research

Safe Reinforcement Learning via Shielding under Partial Observability

Author(s): Steven Carr, Nils Jansen, Sebastian Junges, Ufuk Topcu
Published in: Proceedings of the AAAI Conference on Artificial Intelligence, Issue 37, 2023, ISSN 2374-3468
Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/AAAI.V37I12.26723

CTMCs with Imprecisely Timed Observations

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

Robust Active Measuring under Model Uncertainty

Author(s): Merlijn Krale, Thiago D. Simão, Jana Tumova, Nils Jansen
Published in: Proceedings of the AAAI Conference on Artificial Intelligence, Issue 38, 2024, ISSN 2374-3468
Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/AAAI.V38I19.30122

More for Less: Safe Policy Improvement with Stronger Performance Guarantees

Author(s): Patrick Wienhöft, Marnix Suilen, Thiago D. Simão, Clemens Dubslaff, Christel Baier, Nils Jansen
Published in: Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 2023
Publisher: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/IJCAI.2023/490

Safe Policy Improvement for POMDPs via Finite-State Controllers

Author(s): Thiago D. Simão, Marnix Suilen, Nils Jansen
Published in: Proceedings of the AAAI Conference on Artificial Intelligence, Issue 37, 2023, ISSN 2374-3468
Publisher: 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

Author(s): Christoph Schmidl, Thiago Simão, Nils Jansen
Published in: Proceedings of the 16th International Conference on Agents and Artificial Intelligence, 2024
Publisher: SCITEPRESS - Science and Technology Publications
DOI: 10.5220/0012473600003636

Imprecise Probabilities Meet Partial Observability: Game Semantics for Robust POMDPs

Author(s): Eline M. Bovy, Marnix Suilen, Sebastian Junges, Nils Jansen
Published in: Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence, 2024
Publisher: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/ijcai.2024/740

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

Author(s): Wietze Koops, Nils Jansen, Sebastian Junges, Thiago D. Simão
Published in: Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 2023
Publisher: 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

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