Zobrazeno 1 - 10
of 12
pro vyhledávání: '"Mohamad Kazem Shirani Faradonbeh"'
Publikováno v:
IEEE Transactions on Automatic Control. 66:1802-1808
The main challenge for adaptive regulation of linear-quadratic systems is the trade-off between identification and control. An adaptive policy needs to address both the estimation of unknown dynamics parameters (exploration), as well as the regulatio
Autor:
Walter L. Leite, Samrat Roy, Nilanjana Chakraborty, George Michailidis, A. Corinne Huggins-Manley, Sidney D'Mello, Mohamad Kazem Shirani Faradonbeh, Emily Jensen, Huan Kuang, Zeyuan Jing
Publikováno v:
LAK22: 12th International Learning Analytics and Knowledge Conference.
Publikováno v:
SSRN Electronic Journal.
Linear dynamical systems are canonical models for learning-based control of plants with uncertain dynamics. The setting consists of a stochastic differential equation that captures the state evolution of the plant understudy, while the true dynamics
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::27f515df69421d00c536956216e55c45
http://arxiv.org/abs/2112.15094
http://arxiv.org/abs/2112.15094
Contextual multi-armed bandits are classical models in reinforcement learning for sequential decision-making associated with individual information. A widely-used policy for bandits is Thompson Sampling, where samples from a data-driven probabilistic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::af18ec51a4c3d7696e94976a608d4425
http://arxiv.org/abs/2110.12175
http://arxiv.org/abs/2110.12175
Publikováno v:
IEEE Transactions on Automatic Control. 64:3498-3505
Stabilization of linear systems with unknown dynamics is a canonical problem in adaptive control. Since the lack of knowledge of system parameters can cause it to become destabilized, an adaptive stabilization procedure is needed prior to regulation.
Publikováno v:
IEEE Transactions on Control of Network Systems. 4:770-780
Network control refers to a very large and diverse set of problems including controllability of linear time-invariant dynamical systems, where the objective is to select an appropriate input to steer the network to a desired state. There are many not
Publikováno v:
Automatica. 117:108950
This paper studies adaptive algorithms for simultaneous regulation (i.e., control) and estimation (i.e., learning) of Multiple Input Multiple Output (MIMO) linear dynamical systems. It proposes practical, easy to implement control policies based on p
Publikováno v:
DSW
Data-driven control strategies for dynamical systems with unknown parameters are popular in theory and applications. An essential problem is to prevent stochastic linear systems becoming destabilized, due to the uncertainty of the decision-maker abou
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4116f1e9a5561cba0b763c5f22fcc823
Publikováno v:
DSW
Principal components analysis (PCA) is a widely used dimension reduction technique with an extensive range of applications. In this paper, an online distributed algorithm is proposed for recovering the principal eigenspaces. We further establish its
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ecdcb9deb177662a9cdc8b2ec7ae7dd5