A Moreau Envelope Approach for LQR Meta-Policy Estimation
A Aravind, MT Toghani, CA Uribe - arXiv preprint arXiv:2403.17364, 2024 - arxiv.org
We study the problem of policy estimation for the Linear Quadratic Regulator (LQR) in
discrete-time linear time-invariant uncertain dynamical systems. We propose a Moreau …
discrete-time linear time-invariant uncertain dynamical systems. We propose a Moreau …
Towards Scalable and Personalized Collaborative Learning
MT Toghani - 2024 - search.proquest.com
This thesis studies collaborative learning framework, where a group of agents cooperate to
learn a powerful model from their local data in a distributed or decentralized manner. We …
learn a powerful model from their local data in a distributed or decentralized manner. We …
[PDF][PDF] Αναστασιος Κυριλλιδης
MT Toghani - 2024 - repository.rice.edu
The rapid growth of data generated by modern applications, such as social media, sensor
networks, and cloud-based databases in various fields, including healthcare, finance, e …
networks, and cloud-based databases in various fields, including healthcare, finance, e …