7期

最新文章

• State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning With Rewards AI翻译
  作者：Calvo-Fullana, Miguel; Paternain, Santiago; Chamon, Luiz F. O.; Ribeiro, Alejandro
  作者单位：Pompeu Fabra University; Rensselaer Polytechnic Institute; University of Stuttgart; University of Pennsylvania
  摘要：A common formulation of constrained reinforcement learning involves multiple rewards that must individually accumulate to given thresholds. In this class of problems, we show a simple example in which the desired optimal policy cannot be induced by any weighted linear combination of rewards. Hence, there exist constrained reinforcement learning problems for which neither regularized nor classical primal-dual methods yield optimal policies. This work addresses this shortcoming by augmenting the...
• Distributional Reachability for Markov Decision Processes: Theory and Applications AI翻译
  作者：Gao, Yulong; Abate, Alessandro; Xie, Lihua; Johansson, Karl Henrik
  作者单位：Imperial College London; University of Oxford; Nanyang Technological University
  摘要：We study distributional reachability for finite Markov decision processes (MDPs) from a control theoretical perspective. Unlike standard probabilistic reachability notions, which are defined over MDP states or trajectories, in this article reachability is formulated over the space of probability distributions. We propose two set-valued maps for the forward and backward distributional reachability problems: the forward map collects all state distributions that can be reached from a set of initi...
• Performance-Barrier-Based Event-Triggered Control With Applications to Network Systems AI翻译
  作者：Ong, Pio; Cortes, Jorge
  作者单位：California Institute of Technology; University of California System; University of California San Diego
  摘要：This article proposes a novel framework for resource-aware control design termed performance-barrier-based triggering. Given a feedback policy, along with a Lyapunov function certificate that guarantees its correctness, we examine the problem of designing its digital implementation through event-triggered control while ensuring a prescribed performance on the certificate's convergence rate is met and triggers occur as sparingly as possible. Our methodology takes into account the performance re...
• Supervisory Control of Networked Discrete Event Systems to Achieve a Required Language AI翻译
  作者：Wang, Xiaojun; Hu, Hesuan; Lin, Feng
  作者单位：University of Shanghai for Science & Technology; Xidian University; Nanyang Technological University; Xi'an Jiaotong University; Wayne State University
  摘要：Because of the wide use of networks, supervisory control of networked discrete event systems becomes more and more important. Since the languages generated by a networked supervisor is nondeterministic due to communication delays and losses, large and small languages are defined. While the large language has been investigated in the literature, the small language has not. In this article, we investigate the small language, which is needed for a supervised system to perform some required tasks....
• On the Equivalence of Contraction and Koopman Approaches for Nonlinear Stability and Control AI翻译
  作者：Yi, Bowen; Manchester, Ian R.
  作者单位：University of Sydney; Universite de Montreal; Polytechnique Montreal; University of Sydney
  摘要：In this article, we prove new connections between two frameworks for analysis and control of nonlinear systems: the Koopman operator framework and contraction analysis. Each method, in different ways, provides exact and global analyses of nonlinear systems by way of linear systems theory. The main results of this article show equivalence between contraction and Koopman approaches for a wide class of stability analysis and control design problems. In particular, the stability or stablizability ...
• Model-Free Nonlinear Feedback Optimization AI翻译
  作者：He, Zhiyu; Bolognani, Saverio; He, Jianping; Dorfler, Florian; Guan, Xinping
  作者单位：Swiss Federal Institutes of Technology Domain; ETH Zurich; Shanghai Jiao Tong University
  摘要：Feedback optimization is a control paradigm that enables physical systems to autonomously reach efficient operating points. Its central idea is to interconnect optimization iterations in a closed loop with the physical plant. Since iterative gradient-based methods are extensively used to achieve optimality, feedback optimization controllers typically require knowledge of the steady-state sensitivity of the plant, which may not be easily accessible in some applications. In contrast, in this art...
• On the Exactness of a Stability Test for Discrete-Time Lur'e Systems With Slope-Restricted Nonlinearities AI翻译
  作者：Kharitenko, Andrey; Scherer, Carsten W.
  作者单位：University of Stuttgart; Eindhoven University of Technology; University of Stuttgart
  摘要：In this note it is shown that the famous multiplier absolute stability test of R. O'Shea, G. Zames, and P. Falb is necessary and sufficient if the set of Lur'e interconnections is lifted to a Kronecker structure. An explicit method to construct the destabilizing static nonlinearity is presented.
• Distributed Nash Equilibrium Seeking for a Class of Uncertain Nonlinear Systems Subject to Bounded Disturbances AI翻译
  作者：Huang, Jie
  作者单位：Chinese University of Hong Kong
  摘要：In this article, we study the problem of the distributed Nash equilibrium seeking of $N$-player games over jointly strongly connected switching networks. The action of each player is governed by a class of uncertain nonlinear systems. Our approach integrates the consensus algorithm, the distributed estimator over jointly strongly connected switching networks, and some adaptive control techniques. Furthermore, we also consider the disturbance rejection problem for bounded disturbances with unkn...
• A Note on Fixed- and Discrete-Time Estimation via the DREM Method AI翻译
  作者：Korotina, Marina; Aranovskiy, Stanislav; Ushirobira, Rosane; Efimov, Denis; Wang, Jian
  作者单位：ITMO University; Universite de Lille; Inria; Centre National de la Recherche Scientifique (CNRS); Hangzhou Dianzi University
  摘要：A simple fixed-time converging estimation algorithm is presented for a linear regression using the dynamic regressor extension and mixing method within a discrete-time setting, with a persistently excited regressor and bounded measurement noises. The solution is based on Kreisselmeier's filters, and it is computationally simpler than the existing analogs.
• Controllability Scores for Selecting Control Nodes of Large-Scale Network Systems AI翻译
  作者：Sato, Kazuhiro; Terasaki, Shun
  作者单位：University of Tokyo
  摘要：To appropriately select control nodes in a large-scale network system, we propose two control centralities called volumetric and average energy controllability scores. The scores are the unique solutions to convex optimization problems formulated using the controllability Gramian. The uniqueness is proven for stable cases and for unstable cases that include multiagent systems. We show that the scores can be efficiently calculated by using a proposed algorithm based on the projected gradient me...