Data-Driven Verification and Learning Under Uncertainty

Informazioni relative al progetto

DEUCE

ID dell’accordo di sovvenzione: 101077178

DOI

10.3030/101077178

Data della firma CE 6 Dicembre 2022

Data di avvio 1 Gennaio 2023

Data di completamento 31 Dicembre 2027

Finanziato da

• European Research Council (ERC)

Costo totale

€ 1 500 000,00

Contributo UE

€ 1 500 000,00

Coordinato da

RUHR-UNIVERSITAET BOCHUM
Germany

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Pubblicazioni

Peer reviewed articles (4)

Decision-making under uncertainty: beyond probabilities

Autori: Thom Badings, Thiago D. Simão, Marnix Suilen, Nils Jansen
Pubblicato in: International Journal on Software Tools for Technology Transfer, Numero 25, 2023, ISSN 1433-2779
Editore: Springer Science and Business Media LLC
DOI: 10.1007/S10009-023-00704-3

Strong Simple Policies for POMDPs

Autori: Leonore Winterer, Ralf Wimmer, Bernd Becker, Nils Jansen
Pubblicato in: International Journal on Software Tools for Technology Transfer, Numero 26, 2024, ISSN 1433-2779
Editore: 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

Autori: Thom Badings, Licio Romao, Alessandro Abate, David Parker, Hasan A. Poonawala, Marielle Stoelinga, Nils Jansen
Pubblicato in: Journal of Artificial Intelligence Research, Numero 76, 2023, ISSN 1076-9757
Editore: AI Access Foundation
DOI: 10.1613/JAIR.1.14253

Parameter synthesis for Markov models: covering the parameter space

Autori: Sebastian Junges, Erika Ábrahám, Christian Hensel, Nils Jansen, Joost-Pieter Katoen, Tim Quatmann, Matthias Volk
Pubblicato in: Formal Methods in System Design, Numero 62, 2024, ISSN 0925-9856
Editore: 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

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

Factored Online Planning in Many-Agent POMDPs

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

Efficient Sensitivity Analysis for Parametric Robust Markov Chains

Autori: Thom Badings, Sebastian Junges, Ahmadreza Marandi, Ufuk Topcu, Nils Jansen
Pubblicato in: Lecture Notes in Computer Science, Computer Aided Verification, 2024
Editore: 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

Autori: Thom Badings, Licio Romao, Alessandro Abate, Nils Jansen
Pubblicato in: 2024 European Control Conference (ECC), 2024
Editore: IEEE
DOI: 10.23919/ECC64448.2024.10590865

Reinforcement Learning by Guided Safe Exploration

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

Approximate Dec-POMDP Solving Using Multi-Agent A*

Autori: Wietze Koops, Sebastian Junges, Nils Jansen
Pubblicato in: Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence, 2024
Editore: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/ijcai.2024/745

Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation

Autori: Yannick Hogewind, Thiago D. Simão, Tal Kachman, Nils Jansen
Pubblicato in: The Eleventh International Conference on Learning Representations, {ICLR} 2023, 2023
Editore: OpenReview.net

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

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

Risk-aware Curriculum Generation for Heavy-tailed Task Distributions

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

Safe Reinforcement Learning via Shielding under Partial Observability

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

CTMCs with Imprecisely Timed Observations

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

Robust Active Measuring under Model Uncertainty

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

More for Less: Safe Policy Improvement with Stronger Performance Guarantees

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

Safe Policy Improvement for POMDPs via Finite-State Controllers

Autori: Thiago D. Simão, Marnix Suilen, Nils Jansen
Pubblicato in: Proceedings of the AAAI Conference on Artificial Intelligence, Numero 37, 2023, ISSN 2374-3468
Editore: 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

Autori: Christoph Schmidl, Thiago Simão, Nils Jansen
Pubblicato in: Proceedings of the 16th International Conference on Agents and Artificial Intelligence, 2024
Editore: SCITEPRESS - Science and Technology Publications
DOI: 10.5220/0012473600003636

Imprecise Probabilities Meet Partial Observability: Game Semantics for Robust POMDPs

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

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

Autori: Wietze Koops, Nils Jansen, Sebastian Junges, Thiago D. Simão
Pubblicato in: Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 2023
Editore: 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

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