Results 21 to 30 of about 171,350 (313)
Journal of the American Statistical Association, 2020 Q-learning is a regression-based approach that is widely used to formalize the development of an optimal dynamic treatment strategy. Finite dimensional working models are typically used to estimate certain nuisance parameters, and misspecification of these working models can result in residual confounding and/or efficiency loss.
Ashkan Ertefaie +3 more
openaire +5 more sources
An Improved Q-Learning Algorithm and Its Application in Path Planning
Taiyuan Ligong Daxue xuebao, 2021 Traditional Q-Learning algorithm has the problems of too many random searches and slow convergence speed. Therefore, in this paper an improved ε-Q-Learning algorithm based on traditional Q-Learning algorithm was propased and applied to path planning. The
Guojun MAO, Shimin GU
doaj +1 more source
The clinical spectrum of SMA‐PME and in vitro normalization of its cellular ceramide profile
Annals of Clinical and Translational Neurology, Volume 9, Issue 12, Page 1941-1952, December 2022., 2022 Abstract Objective The objectives of this study were to define the clinical and biochemical spectrum of spinal muscular atrophy with progressive myoclonic epilepsy (SMA‐PME) and to determine if aberrant cellular ceramide accumulation could be normalized by enzyme replacement.
Michelle M. Lee +16 more
wiley +1 more source
Adaptive Control of an Inverted Pendulum by a Reinforcement Learningbased LQR Method
Sakarya Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 2023 Inverted pendulums constitute one of the popular systems for benchmarking control algorithms. Several methods have been proposed for the control of this system, the majority of which rely on the availability of a mathematical model.
Uğur Yıldıran
doaj +1 more source
Cybernetics and Information Technologies, 2023 Fog computing is one of the emerging forms of cloud computing which aims to satisfy the ever-increasing computation demands of the mobile applications. Effective offloading of tasks leads to increased efficiency of the fog network, but at the same time ...
Bhargavi K. +2 more
doaj +1 more source
Data‐driven performance metrics for neural network learning
International Journal of Adaptive Control and Signal Processing, EarlyView., 2023 Summary Effectiveness of data‐driven neural learning in terms of both local mimima trapping and convergence rate is addressed. Such issues are investigated in a case study involving the training of one‐hidden‐layer feedforward neural networks with the extended Kalman filter, which reduces the search for the optimal network parameters to a state ...
Angelo Alessandri +2 more
wiley +1 more source
Mathematical Biosciences and Engineering, 2023 In the control of the self-driving vehicles, PID controllers are widely used due to their simple structure and good stability. However, in complex self-driving scenarios such as curvature curves, car following, overtaking, etc., it is necessary to ensure
Yongqiang Yao +5 more
doaj +1 more source
IEEE Access, 2023 The current application of control theory is commonly carried out in systems with a model or known system dynamics. However, in practice this is a formidable task to achieve as not all state information can be known. The use of the Output Feedback (OPFB)
Adi Novitarini Putri +3 more
doaj +1 more source
Prospect-theoretic Q-learning [PDF]
Systems & Control Letters, 2021 Published in Systems and Control Letters.
Vivek S. Borkar, Siddharth Chandak
openaire +3 more sources
A Variational Beam Model for Failure of Cellular and Truss‐Based Architected Materials
Advanced Engineering Materials, EarlyView., 2023 Herein, a versatile and efficient beam modeling framework is developed to predict the nonlinear response and failure of cellular, truss‐based, and woven architected materials. It enables the exploration of their design space and the optimization of their mechanical behavior in the nonlinear regime. A variational formulation of a beam model is presented
Konstantinos Karapiperis +3 more
wiley +1 more source