-
作者：Zhang, Kaiqing; Yang, Zhuoran; Liu, Han; Zhang, Tong; Basar, Tamer
作者单位：University of Illinois System; University of Illinois Urbana-Champaign; University of Illinois System; University of Illinois Urbana-Champaign; Princeton University; Northwestern University; Hong Kong University of Science & Technology
摘要：Despite the increasing interest in multiagent reinforcement learning (MARL) in multiple communities, understanding its theoretical foundation has long been recognized as a challenging problem. In this article, we address this problem by providing a finite-sample analysis for decentralized batch MARL. Specifically, we consider a type of mixed MARL setting with both cooperative and competitive agents, where two teams of agents compete in a zero-sum game setting, while the agents within each team...
-
作者：Stuerz, Yvonne R.; Eichler, Annika; Smith, Roy S.
作者单位：University of California System; University of California Berkeley; Helmholtz Association; Deutsches Elektronen-Synchrotron (DESY); Swiss Federal Institutes of Technology Domain; ETH Zurich
摘要：This article presents scalable controller synthesis methods for heterogeneous and partially heterogeneous systems. First, heterogeneous systems composed of different subsystems that are interconnected over a directed graph are considered. Techniques from robust and gain-scheduled controller synthesis are employed, in particular, the full-block S-procedure, to deal with the decentralized system part in a nominal condition and with the interconnection part in a multiplier condition. Under some s...
-
作者：Schlueter, Henning; Solowjow, Friedrich; Trimpe, Sebastian
作者单位：University of Stuttgart; Max Planck Society; RWTH Aachen University
摘要：When models are inaccurate, the performance of model-based control will degrade. For linear quadratic control, an event-triggered learning framework is proposed that automatically detects inaccurate models and triggers the learning of a new process model when needed. This is achieved by analyzing the probability distribution of the linear quadratic cost and designing a learning trigger that leverages Chernoff bounds. In particular, whenever empirically observed cost signals are located outside...
-
作者：Sun, Chao; Hu, Guoqiang
作者单位：Nanyang Technological University
摘要：In this article, we propose centralized and distributed continuous-time penalty methods to find a Nash equilibrium for a generalized noncooperative game with shared inequality and equality constraints and private inequality constraints that depend on the player itself. By using the l(1) penalty function, we prove that the equilibrium of a differential inclusion is a normalized Nash equilibrium of the original generalized noncooperative game, and the centralized differential inclusion exponenti...
-
作者：Herzallah, Randa
作者单位：Aston University
摘要：This article studies model reference adaptive control (MRAC) for a class of stochastic discrete time control systems with time delays in the control input. In particular, a unified fully probabilistic control framework is established to develop the solution to the MRAC, where the controller is the minimizer of the Kullback-Leibler divergence between the actual and desired joint probability density functions of the tracking error and the controller. The developed framework is quite general, whe...
-
作者：Andrieu, Vincent; Jayawardhana, Bayu; Praly, Laurent
作者单位：Universite Claude Bernard Lyon 1; Centre National de la Recherche Scientifique (CNRS); University of Groningen; Universite PSL; MINES ParisTech
摘要：We study the relationship between the global exponential stability of an invariant manifold and the existence of a positive semidefinite Riemannian metric which is contracted by the flow. In particular, we investigate how the following properties are related to each other (in the global case): 1) A manifold is globally transversally exponentially stable; 2) the corresponding variational system admits the same property; 3) there exists a degenerate Riemannian metric which is contracted by the f...
-
作者：Berneburg, James; Nowzari, Cameron
作者单位：George Mason University
摘要：This article revisits the classical multiagent average consensus problem for which many different event-triggered control strategies have been proposed over the last decade. Many of the earliest versions of these works conclude asymptotic stability without proving that Zeno behavior, or deadlocks, do not occur along the trajectories of the system. More recent works that resolve this issue either: propose the use of a dwell time that forces interevent times to be lower bounded away from zero bu...
-
作者：Song, Yunxia; Michiels, Wim; Zhou, Bin; Duan, Guang-Ren
作者单位：Harbin Institute of Technology; KU Leuven
摘要：This article is concerned with the strong stability problem of linear continuous-time delay-difference equations with multiple time delays. A family of linear matrix inequalities (LMIs), indexed by a positive integer k, is derived to assess strong stability. A time-domain interpretation of the proposed LMI-based condition is given in terms of a quadratic integral Lyapunov functional, which allows us to reveal relations with an existing result. The LMI condition can easily be reformulated in a ...
-
作者：Chang, Dong Eui
作者单位：Korea Advanced Institute of Science & Technology (KAIST)
摘要：In this article globally exponentially convergent continuous observers for invariant kinematic systems on finite-dimensional matrix Lie groups has been proposed. Such an observer estimates, from measurements of landmarks, vectors, and biased velocity, both the system state and the unknown constant bias in velocity measurement, where the state belongs to the state-space Lie group and the velocity to the Lie algebra of the Lie group. The main technique is to embed a given system defined on a mat...
-
作者：Bae, Yoo-Bin; Lim, Young-Hun; Ahn, Hyo-Sung
作者单位：Gwangju Institute of Science & Technology (GIST); Gyeongnam National University of Science and Technology
摘要：In this article, we present a distributed robust adaptive gradient controller for distance-based formation systems with exogenous disturbances. Based on the proposed controller, we consider two undirected formation topologies: Minimally infinitesimally rigid formation and nonminimally infinitesimally rigid formation. For both formation systems, we show that the distributed robust adaptive gradient controller guarantees a local stability of formation systems with exogenous disturbances. Further...
