Results 1 to 10 of about 2,413,760 (324)
Learning-based Robust Motion Planning with Guaranteed Stability: A Contraction Theory Approach [PDF]
IEEE Robotics and Automation Letters, 2021 This paper presents Learning-based Autonomous Guidance with RObustness and Stability guarantees (LAG-ROS), which provides machine learning-based nonlinear motion planners with formal robustness and stability guarantees, by designing a differential Lyapunov function using contraction theory.
Hiroyasu Tsukamoto, Soon‐Jo Chung
arxiv +12 more sources
Contraction Theory for Nonlinear Stability Analysis and Learning-based Control: A Tutorial Overview [PDF]
Annual Reviews in Control; Volume 52; 2021; Pages 135-169; ISSN
1367-5788,, 2021 Contraction theory is an analytical tool to study differential dynamics of a non-autonomous (i.e., time-varying) nonlinear system under a contraction metric defined with a uniformly positive definite matrix, the existence of which results in a necessary and sufficient characterization of incremental exponential stability of multiple solution ...
Hiroyasu Tsukamoto +2 more
arxiv +11 more sources
Evaluation of Goaf Stability Based on Transfer Learning Theory of Artificial Intelligence [PDF]
IEEE Access, 2019 Current artificial intelligence models for evaluating goaf stability in underground metal mines need a large amount of sample data for training, and their accuracy declines with small sample size. With the aim of solving this problem, this paper proposes
Yaguang Qin +4 more
doaj +5 more sources
On Solutions and Stability of Stochastic Functional Equations Emerging in Psychological Theory of Learning [PDF]
Axioms, 2022 We show how to apply the well-known fixed-point approach in the study of the existence, uniqueness, and stability of solutions to some particular types of functional equations. Moreover, we also obtain the Ulam stability result for them.
Ali Turab, Janusz Brzdęk, Wajahat Ali
doaj +3 more sources
International Journal of Analysis and Applications, 2023 The psychological learning theory (PLT) in the formation of moral verdict is represented by the choice-practice paradigm. It involves weighing the effects of various options and choosing one to put into practice.
Doha A. Kattan, Hasanen A. Hammad
doaj +4 more sources
Actor-Critic Reinforcement Learning for Control with Stability Guarantee [PDF]
IEEE Robotics and Automation Letters, 2020 Reinforcement Learning (RL) and its integration with deep learning have achieved impressive performance in various robotic control tasks, ranging from motion planning and navigation to end-to-end visual manipulation.
Han, Minghao +3 more
core +3 more sources
Stability-Guaranteed Reinforcement Learning for Contact-rich Manipulation [PDF]
arXiv, 2020 Reinforcement learning (RL) has had its fair share of success in contact-rich manipulation tasks but it still lags behind in benefiting from advances in robot control theory such as impedance control and stability guarantees. Recently, the concept of variable impedance control (VIC) was adopted into RL with encouraging results.
S. A. Khader +3 more
arxiv +3 more sources
Learning Deep Energy Shaping Policies for Stability-Guaranteed Manipulation [PDF]
arXiv, 2021 Deep reinforcement learning (DRL) has been successfully used to solve various robotic manipulation tasks. However, most of the existing works do not address the issue of control stability. This is in sharp contrast to the control theory community where the well-established norm is to prove stability whenever a control law is synthesized.
S. A. Khader +3 more
arxiv +3 more sources
The Bayesian Stability Zoo [PDF]
arXiv, 2023 We show that many definitions of stability found in the learning theory literature are equivalent to one another. We distinguish between two families of definitions of stability: distribution-dependent and distribution-independent Bayesian stability.
Shay Moran +2 more
arxiv +2 more sources
Stability and Generalization of Stochastic Compositional Gradient Descent Algorithms [PDF]
arXiv, 2023 Many machine learning tasks can be formulated as a stochastic compositional optimization (SCO) problem such as reinforcement learning, AUC maximization, and meta-learning, where the objective function involves a nested composition associated with an expectation. While a significant amount of studies has been devoted to studying the convergence behavior
Wei, Xiyuan +3 more
arxiv +2 more sources