We present a learning method to learn the mapping from an input space to an action space, which is particularly suitable when the action is an optimal decision with respect to a certain unknown cost function. We use an inverse optimization approach to retrieve the cost function by introducing a new loss function and a new hypothesis class of mappings. A tractable convex reformulation of the learning problem is also presented. The method is effective for learning input-action mapping in continuous input-action space with input-output constraints, typically present in control systems. The learning approach can be effectively transformed to learn a Model Predictive Control (MPC) behaviour and a case study to mimic an MPC is presented, which is a rather computationally heavy control strategy. Simulation and experimental results show the effectiveness of the proposed approach.
|Title of host publication||Proceedings of the American Control Conference, ACC 2021|
|Publication status||Published - 2021|
|Event||2021 American Control Conference, ACC 2021 - Virtual, New Orleans, United States|
Duration: 25 May 2021 → 28 May 2021
|Conference||2021 American Control Conference, ACC 2021|
|City||Virtual, New Orleans|
|Period||25/05/21 → 28/05/21|
Bibliographical noteGreen Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.