2024

最新文章

• Tailoring Gradient Methods for Differentially Private Distributed Optimization AI翻译
  作者：Wang, Yongqiang; Nedic, Angelia
  作者单位：Clemson University; Arizona State University; Arizona State University-Tempe
  摘要：Decentralized optimization is gaining increased traction due to its widespread applications in large-scale machine learning and multiagent systems. The same mechanism that enables its success, i.e., information sharing among participating agents, however, also leads to the disclosure of individual agents' private information, which is unacceptable when sensitive data are involved. As differential privacy is becoming a de facto standard for privacy preservation, recently results have emerged in...
• On Contractive Port-Hamiltonian Systems With State-Modulated Interconnection and Damping Matrices AI翻译
  作者：Yaghmaei, Abolfazl; Yazdanpanah, Mohammad Javad
  作者单位：University of Tehran; University of Tehran
  摘要：In this article, for the input-state-output class of port-Hamiltonian systems, the contraction property is characterized. Recently, some results on contraction of port-Hamiltonian systems with constant interconnection and damping matrices have been published. This article extends these results for state-modulated interconnection and damping matrices. In this regard, the powerful method of interconnection and damping assignment passivity-based control is extended for tracking designs. Controlle...
• Data-Driven Feedback Linearization Using the Koopman Generator AI翻译
  作者：Gadginmath, Darshan; Krishnan, Vishaal; Pasqualetti, Fabio
  作者单位：University of California System; University of California Riverside; Harvard University
  摘要：This article contributes a theoretical framework for data-driven feedback linearization of nonlinear control-affine systems. We unify the traditional geometric perspective on feedback linearization with an operator-theoretic perspective involving the Koopman operator. We first show that if the distribution of the control vector field and its repeated Lie brackets with the drift vector field is involutive, then there exists an output and a feedback control law for which the Koopman generator is...
• Data-Driven Polytopic Output Synchronization From Noisy Data AI翻译
  作者：Li, Yifei; Liu, Wenjie; Wang, Gang; Sun, Jian; Xie, Lihua; Chen, Jie
  作者单位：Beijing Institute of Technology; Nanyang Technological University; Tongji University
  摘要：This article proposes a novel approach to address the output synchronization problem for unknown heterogeneous multiagent systems (MASs) using noisy data. Unlike existing studies that focus on noiseless data, we introduce a distributed data-driven controller that enables all heterogeneous followers to synchronize with a leader's output trajectory. To handle the noise in the state-input-output data, we develop a data-based polytopic representation for the MAS. We tackle the issue of infeasibili...
• Incorporation of Likely Future Actions of Agents Into Pseudo-Gradient Dynamics of Noncooperative Games AI翻译
  作者：Yan, Yuyue; Hayakawa, Tomohisa
  作者单位：Institute of Science Tokyo; Tokyo Institute of Technology
  摘要：In this article, we connect cognitive hierarchy theory with the pseudo-gradient dynamics in noncooperative systems to extend the pseudo-gradient dynamics with some prediction behaviors under level-k thinking. In this framework, each agent believes that he is the most sophisticated person in the noncooperative system and makes the proactive decision according to some strategic reasoning of the other agents' likely actions. Depending on a knowledge network of payoff functions, the modified pseud...
• Distributed Multiagent Reinforcement Learning Based on Graph-Induced Local Value Functions AI翻译
  作者：Jing, Gangshan; Bai, He; George, Jemin; Chakrabortty, Aranya; Sharma, Piyush K.
  作者单位：Chongqing University; Oklahoma State University System; Oklahoma State University - Stillwater; United States Department of Defense; US Army Research, Development & Engineering Command (RDECOM); US Army Research Laboratory (ARL); North Carolina State University
  摘要：Achieving distributed reinforcement learning (RL) for large-scale cooperative multiagent systems (MASs) is challenging because: 1) each agent has access to only limited information and 2) issues on scalability and sample efficiency emerge due to the curse of dimensionality. In this article, we propose a general distributed framework for sample efficient cooperative multiagent reinforcement learning (MARL) by utilizing the structures of graphs involved in this problem. We introduce three coupli...
• Sampled-Data Feedback Stabilization in Mean Square for Stochastic Homogeneous Systems AI翻译
  作者：Yu, Xin; Lin, Wei
  作者单位：Jiangsu Normal University; University System of Ohio; Case Western Reserve University
  摘要：For stochastic nonlinear systems which are only continuous but not necessarily local Lipschitz nor linear growth, we study the problem of asymptotic stabilization in mean square (AS-in-MS) via sampled-data feedback. We begin by establishing the existence of solutions for a class of hybrid stochastic systems. With the aid of weighted homogeneity, we then prove that for stochastic homogeneous systems of degree zero, asymptotic stabilizability in mean square by homogeneous feedback implies asympt...
• Active Learning-Based Model Predictive Coverage Control AI翻译
  作者：Rickenbach, Rahel; Kohler, Johannes; Scampicchio, Anna; Zeilinger, Melanie N.; Carron, Andrea
  作者单位：Swiss Federal Institutes of Technology Domain; ETH Zurich
  摘要：The problem of coverage control, i.e., of coordinating multiple agents to optimally cover an area, arises in various applications. However, coverage applications face two major challenges: 1) dealing with nonlinear dynamics while respecting system and safety critical constraints and 2) performing the task in an initially unknown environment. We solve the coverage problem by using a hierarchical framework, in which references are calculated at a central server and passed to the agents' local mo...
• Finite-Time Annular Domain Stability and Asynchronous H∞ Control for Stochastic Switching Markov Jump Systems AI翻译
  作者：Zhang, Weihai; Zhong, Shiyu; Jiang, Xiushan
  作者单位：Shandong University of Science & Technology; China University of Petroleum
  摘要：This article mainly investigates the stochastic finite-time annular domain stability (SFTADS) and asynchronous H-infinity control for nonlinear stochastic switching Markov jump systems (SMJSs). First, the criterion of SFTADS of the system is given by the mode-dependent average dwell time method, and two results, which consider particular cases with no switching signal and no Markov jump, are obtained. Second, when there are asynchronous phenomena in both deterministic switching and Markov jump...
• Approximation by Simple Poles-Part I: Density and Geometric Convergence Rate in Hardy Space AI翻译
  作者：Fisher, Michael W.; Hug, Gabriela; Dorfler, Florian
  作者单位：University of Waterloo; Swiss Federal Institutes of Technology Domain; ETH Zurich
  摘要：Optimal linear feedback control design is a valuable but challenging problem due to the nonconvexity of the underlying optimization and the infinite dimensionality of the Hardy space of stabilizing controllers. A powerful class of techniques for solving optimal control problems involves using reparameterization to transform the control design into a convex but infinite-dimensional optimization. To make the problem tractable, historical work focuses on Galerkin-type finite-dimensional approxima...