Identification and adaptive control of markov jump systems: Sample complexity and regret bounds
Learning how to effectively control unknown dynamical systems is crucial for intelligent
autonomous systems. This task becomes a significant challenge when the underlying …
autonomous systems. This task becomes a significant challenge when the underlying …
Finite sample identification of bilinear dynamical systems
Bilinear dynamical systems are ubiquitous in many different domains and they can also be
used to approximate more general control-affine systems. This motivates the problem of …
used to approximate more general control-affine systems. This motivates the problem of …
System identification in presence of undetectable packet losses in the actuation path
A Mohammadzadeh… - Transactions of the …, 2024 - journals.sagepub.com
Identification of networked systems over communication links with packet losses is
considered. It is assumed that there is no connection from the actuators to the system …
considered. It is assumed that there is no connection from the actuators to the system …
Strong consistency and rate of convergence of switched least squares system identification for autonomous markov jump linear systems
In this article, we investigate the problem of system identification for autonomous Markov
jump linear systems (MJS) with complete state observations. We propose switched least …
jump linear systems (MJS) with complete state observations. We propose switched least …
Regret-Guaranteed Safe Switching with Minimum Cost: LQR Setting with Unknown Dynamics
JA Chekan, C Langbort - arXiv preprint arXiv:2302.02270, 2023 - arxiv.org
Externally Forced Switched (EFS) systems represent a subset of switched systems where
switches occur deliberately to meet an external requirement. However, fast switching can …
switches occur deliberately to meet an external requirement. However, fast switching can …
[图书][B] The Sample Complexity of Learning Dynamical Systems
Y Sattar - 2023 - search.proquest.com
Abstract Machine learning has emerged as a leading force in revolutionizing technology,
education, and almost every aspect of our lives. Reinforcement learning is a sub-field of …
education, and almost every aspect of our lives. Reinforcement learning is a sub-field of …
Learning, Control, and Reduction for Markov Jump Systems
Z Du - 2023 - deepblue.lib.umich.edu
Many real-world phenomena or systems with temporally changing dynamics can be
effectively characterized by time-varying models—typically ensembles of simple models …
effectively characterized by time-varying models—typically ensembles of simple models …