1,357,382 research outputs found
Asymptotic variance of subspace methods by data orthogonalization andmodel decoupling: a comparative analysis
No full textThis is a companion of the paper Chiuso and Picci (2004d) where we do asymptotic error analysis of a weighted PI-MOESP type method and compare accuracy with respect to estimates obtained by customary “joint” subspace methods. The analysis shows that, under certain conditions, methods based on orthogonal decomposition of the input–output data and block-decoupled parametrization perform better than traditional joint-model based methods in the circumstance of nearly parallel regressors
Estimating Koopman operators for nonlinear dynamical systems: A nonparametric approach
Get PDFThe Koopman operator provides a linear description of non-linear systems exploiting an embedding into an infinite dimensional space. Dynamic Mode Decomposition and Extended Dynamic Mode Decomposition are amongst the most popular finite dimensional approximations of the Koopman Operator. In this paper we capture their core essence as a dual version of the same problem, embedding them into the Kernel framework. To do so, we leverage the RKHS as a suitable space for learning the Koopman dynamics. Learning from finite length data automatically provides a finite dimensional approximation induced by data. Simulations and comparison with standard procedures are included
Value-function estimation and uncertainty propagation in Reinforcement Learning: a Koopman operator approach
No full textControl-oriented regularization for linear system identification
No full textIn this paper, we develop a novel theoretical framework for control-oriented identification, based on a Bayesian perspective on modeling. Specifically, we show that closed-loop specifications can be incorporated within the identification procedure as a prior of the model probability distribution via suitable regularization. The corresponding kernel varies according to the additional penalty term and provides a new insight on control-oriented identification. As a secondary contribution, we derive a Bayesian robust control design approach exploiting all the information coming from the above modeling procedure, including the estimate of the uncertainty set The effectiveness of the proposed strategy against state-of-the-art regularized identification is illustrated on a benchmark example for digital control system design
Data-Driven Control of Nonlinear Systems: Learning Koopman Operators for Policy Gradient
No full textData-driven control of nonlinear dynamical systems is a largely open problem. In this paper, building upon the theory of Koopman operators and exploiting ideas from policy gradient methods in reinforcement learning, a novel approach for data-driven optimal control of unknown nonlinear dynamical systems is introduced
- …
