Publications

@workingpaper{Simpson2022,

title = {Parameter Estimation of Linear Dynamical Systems with Gaussian Noise},

author = {Léo Simpson and Andrea Ghezzi and Jonas Asprion and Moritz Diehl},

url = {https://arxiv.org/abs/2211.12302},

doi = {10.48550/ARXIV.2211.12302},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

publisher = {arXiv},

keywords = {},

pubstate = {published},

tppubtype = {workingpaper}

}

@workingpaper{acerboEvaluationMPCbasedImitation2022,

title = {Evaluation of MPC-based Imitation Learning for Human-like Autonomous Driving},

author = {Flavia Sofia Acerbo and Jan Swevers and Tinne Tuytelaars and Tong Duy Son},

doi = {10.48550/arXiv.2211.12111},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

number = {arXiv:2211.12111},

publisher = {arXiv},

keywords = {},

pubstate = {published},

tppubtype = {workingpaper}

}

@workingpaper{bodardSPOCKProximalMethod2022,

title = {SPOCK: A Proximal Method for Multistage Risk-Averse Optimal Control Problems},

author = {Alexander Bodard and Ruairi Moran and Mathijs Schuurmans and Panagiotis Patrinos and Pantelis Sopasakis},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

number = {arXiv:2212.01110},

publisher = {arXiv},

keywords = {},

pubstate = {published},

tppubtype = {workingpaper}

}

@workingpaper{coppensPolicyIterationUsing2022,

title = {Policy Iteration Using Q-functions: Linear Dynamics with Multiplicative Noise},

author = {Peter Coppens and Panagiotis Patrinos},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

number = {arXiv:2212.01192},

publisher = {arXiv},

keywords = {},

pubstate = {published},

tppubtype = {workingpaper}

}

@workingpaper{lahrZeroOrderOptimizationGaussian2022,

title = {Zero-Order Optimization for Gaussian Process-based Model Predictive Control},

author = {Amon Lahr and Andrea Zanelli and Andrea Carron and Melanie N. Zeilinger},

doi = {10.48550/arXiv.2211.15522},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

number = {arXiv:2211.15522},

publisher = {arXiv},

keywords = {},

pubstate = {published},

tppubtype = {workingpaper}

}

@workingpaper{rotaruTightConvergenceRates2022,

title = {Tight Convergence Rates of the Gradient Method on Smooth Hypoconvex Functions},

author = {Teodor Rotaru and Franc cois Glineur and Panagiotis Patrinos},

doi = {10.48550/arXiv.2203.00775},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

number = {arXiv:2203.00775},

publisher = {arXiv},

keywords = {},

pubstate = {published},

tppubtype = {workingpaper}

}

@workingpaper{schuurmansSafeLearningBasedMPC2022,

title = {Safe, Learning-Based MPC for Highway Driving under Lane-Change Uncertainty: A Distributionally Robust Approach},

author = {Mathijs Schuurmans and Alexander Katriniok and Christopher Meissen and H. Eric Tseng and Panagiotis Patrinos},

doi = {10.48550/arXiv.2206.13319},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

number = {arXiv:2206.13319},

publisher = {arXiv},

keywords = {},

pubstate = {published},

tppubtype = {workingpaper}

}

@workingpaper{Lowenstein2022PhysicsInformed,

title = {Physics-Informed Online Learning of Gray-box Models by Moving Horizon Estimation},

author = {Kristoffer Fink Løwenstein and Lorenzo Fagiano and Daniele Bernardini and Alberto Bemporad},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

abstract = {A simple yet expressive prediction model is an essential ingredient in model-based control and estimation. Models derived from fundamental physical principles may fail to capture the complexity of the actual system dynamics. A potential solution is the use of a physics-informed, or gray-box model that extends a physics-based model with a data-driven part. Learning the latter might be challenging, due to noisy measurements and lack of full state information. This work presents a method based on Moving Horizon Estimation (MHE) for simultaneous state estimation and training of a neural network submodel. The method can be used in offline training or applied online for adaptation without any prior knowledge than the white-box submodel. We analyze the capabilities of the method in a two degree of freedom robotic manipulator case study, also showing how it can be used for online adaptation to cope with a time-varying model mismatch},

note = {Under review},

keywords = {},

pubstate = {published},

tppubtype = {workingpaper}

}

@workingpaper{wang2021shaq,

title = {SHAQ: Incorporating Shapley Value Theory into Multi-Agent Q-Learning},

author = {Jianhong Wang and Jinxin Wang and Yuan Zhang and Yunjie Gu and Tae-Kyun Kim},

url = {https://arxiv.org/abs/2105.15013},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

journal = {arXiv preprint arXiv:2105.15013},

keywords = {},

pubstate = {published},

tppubtype = {workingpaper}

}

@workingpaper{laudeConjugateDualitiesRelative2021,

title = {Conjugate Dualities for Relative Smoothness and Strong Convexity under the Light of Generalized Convexity},

author = {Emanuel Laude and Andreas Themelis and Panagiotis Patrinos},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

number = {arXiv:2112.08886},

publisher = {arXiv},

keywords = {},

pubstate = {published},

tppubtype = {workingpaper}

}