-
作者：Usevitch, James; Panagou, Dimitra
作者单位：University of Michigan System; University of Michigan
摘要：Control barrier functions (CBFs) have recently become a powerful method for rendering desired safe sets forward invariant in single-agent and multiagent systems. In the multiagent case, prior literature has considered scenarios where all agents cooperate to ensure that the corresponding set remains invariant. However, these works do not consider scenarios where a subset of the agents are behaving adversarially with the intent to violate safety bounds. In addition, prior results on multiagent C...
-
作者：Fattahi, Salar; Josz, Cedric; Ding, Yuhao; Mohammadi, Reza; Lavaei, Javad; Sojoudi, Somayeh
作者单位：University of Michigan System; University of Michigan; Columbia University; University of California System; University of California Berkeley
摘要：In this article, we study the landscape of an online nonconvex optimization problem, for which the input data vary over time and the solution is a trajectory rather than a single point. To understand the complexity of finding a global solution of this problem, we introduce the notion of spurious (i.e., nonglobal) local trajectory as a generalization to the notion of spurious local solution in nonconvex (time-invariant) optimization. We develop an ordinary differential equation (ODE) associated...
-
作者：Possieri, Corrado; Frasca, Mattia; Rizzo, Alessandro
作者单位：Consiglio Nazionale delle Ricerche (CNR); Istituto di Analisi dei Sistemi ed Informatica Antonio Ruberti (IASI-CNR); University of Catania; Polytechnic University of Turin; New York University; New York University Tandon School of Engineering
摘要：We characterize the reachability probabilities in stochastic directed graphs by means of reinforcement learning methods. In particular, we show that the dynamics of the transition probabilities in a stochastic digraph can be modeled via a difference inclusion, which, in turn, can be interpreted as a Markov decision process. Using the latter framework, we offer a methodology to design reward functions to provide upper and lower bounds on the reachability probabilities of a set of nodes for stoc...
-
作者：Ju, Yue; Mu, Biqiang; Ljung, Lennart; Chen, Tianshi
作者单位：The Chinese University of Hong Kong, Shenzhen; Shenzhen Research Institute of Big Data; The Chinese University of Hong Kong, Shenzhen; Chinese Academy of Sciences; Academy of Mathematics & System Sciences, CAS; Linkoping University
摘要：Regularized techniques, also named as kernel-based techniques, are the major advances in system identification in the last decade. Although many promising results have been achieved, their theoretical analysis is far from complete and there are still many key problems to be solved. One of them is the asymptotic theory, which is about convergence properties of the model estimators as the sample size goes to infinity. The existing related results for regularized system identification are about t...
-
作者：Liang, Xiao; Xu, Juanjuan; Wang, Hongxia; Zhang, Huanshui
作者单位：Linyi University; Shandong University; Shandong University of Science & Technology
摘要：This article considers the decentralized linear-quadratic-Gaussian control problem for discrete-time decentralized system controlled by two players. In this scenario, player 1 shares a unit delayed observations and control inputs with the controller of player 2, whereas due to the limiting capacity, the controller of player 1 cannot obtain the observations and control inputs of player 2, which leads to the asymmetric one-step delay information. It should be emphasized that this structure makes...
-
作者：Schiffer, Johannes; Efimov, Denis
作者单位：Universite de Lille; Centrale Lille; Inria; Centre National de la Recherche Scientifique (CNRS); CNRS - Institute for Information Sciences & Technologies (INS2I)
摘要：We present new results for the analysis of global boundedness of state periodic systems. Thereby, we address both the case of systems, whose dynamics is periodic with respect to a part of the state vector, and the case of systems, whose dynamics is periodic with respect to all state variables. To derive the results, the notion of strong Leonov functions is introduced. The main results are complemented by a number of relaxations based on the concept of weak Leonov functions.
-
作者：Chen, Zebin; Chen, Xuesong; Sun, Hui-Jie
作者单位：Guangdong University of Technology; Sun Yat Sen University
摘要：In this article, some convergence conditions are investigated for the multiple tuning parameters iterative algorithm (MIA) and the single tuning parameter iterative algorithm (SIA), which are proposed to solve the discrete periodic Lyapunov matrix equations related to discrete-time linear periodic systems. First, when all the tuning parameters are selected in the interval (0, 1] and the initial conditions are arbitrarily given, it is proven that the MIA is convergent if and only if the discret...
-
作者：Khatana, Vivek; Salapaka, Murti V.
作者单位：University of Minnesota System; University of Minnesota Twin Cities
-
作者：Li, Kuo; Ahn, Choon Ki; Zheng, Wei Xing; Hua, Chang-Chun
作者单位：Yanshan University; Korea University; Western Sydney University
摘要：This article investigates the problem of the fixed directed topology-based leader-following consensus control for nonlinear multiagent systems with output delays. Diverging from existing results, this study focuses on large time-varying output delay. Taking this condition into account, a novel delay classification-based distributed output feedback consensus algorithm is developed. First, we divide the output delay into two types through a designed constant and introduce a switching signal to d...
-
作者：Osinenko, Pavel; Dobriborsci, Dmitrii; Yaremenko, Grigory; Malaniya, Georgiy
作者单位：Skolkovo Institute of Science & Technology
摘要：A common setting of reinforcement learning (RL) is a Markov decision process (MDP) in which the environment is a stochastic discrete-time dynamical system. Whereas MDPs are suitable in such applications as video games or puzzles, physical systems are time continuous. A general variant of RL is of digital format, where updates of the value (or cost) and policy are performed at discrete moments in time. The agent-environment loop then amounts to a sampled system, whereby sample-and-hold is a spe...
