Cyprien Tamekue,Ruiqi Chen,ShiNung Ching
Cyprien Tamekue
This paper investigates the controllability of a broad class of recurrent neural networks widely used in theoretical neuroscience, including models of large-scale human brain dynamics. Motivated by emerging applications in non-invasive neur...
Robust Control Barrier Functions for Uncertain Parameter-Varying Control Affine Systems with Set-Membership Parameter Estimation [0.03%]
具有集合成员参数估计的不确定时变控制仿射系统的鲁棒控制障碍函数
Tarun Pati,Sze Zheng Yong
Tarun Pati
This paper introduces robust control barrier functions for uncertain parameter-varying control affine systems, where the parametric uncertainties can be time-varying and nonlinearly affecting the system dynamics and/or safety sets. In parti...
Sina Jahandari,Jeffrey Shaman
Sina Jahandari
In this article, we address the problem of estimating a particular transfer function in a dynamic network where the unknown noise processes are potentially correlated across the nodes. It is assumed that the noise correlations are affine in...
Generalized Policy Improvement Algorithms with Theoretically Supported Sample Reuse [0.03%]
具有理论支持的样本重用的广义策略改进算法
James Queeney,Ioannis Ch Paschalidis,Christos G Cassandras
James Queeney
We develop a new class of model-free deep reinforcement learning algorithms for data-driven, learning-based control. Our Generalized Policy Improvement algorithms combine the policy improvement guarantees of on-policy methods with the effic...
Transient Analysis of Serial Production Lines With Perishable Products: Bernoulli Reliability Model [0.03%]
易逝品串联生产流水线的暂态分析：伯努利可靠性模型
Feng Ju,Jingshan Li,John A Horst
Feng Ju
Manufacturing systems with perishable products are widely observed in practice (e.g., food industry, biochemical productions, battery and semiconductor manufacturing). In such systems, the quality of the product is highly affected by its ex...
Solid Boundary Output Feedback Control of the Stefan Problem: The Enthalpy Approach [0.03%]
熵方法在Stefan问题固体边界反馈控制中的应用
Bryan Petrus,Zhelin Chen,Hamza El-Kebir et al.
Bryan Petrus et al.
By taking enthalpy-an internal energy of a diffusion-type system-as the system state and expressing it in terms of the temperature profile and the phase-change interface position, the output feedback boundary control laws for a fundamentall...
Ashkan Zehfroosh,Herbert G Tanner
Ashkan Zehfroosh
This paper presents a theoretical framework for probably approximately correct (PAC) multi-agent reinforcement learning (MARL) algorithms for Markov games. Using the idea of delayed Q-learning, the paper extends the well-known Nash Q-learni...
A Sharp Estimate on the Transient Time of Distributed Stochastic Gradient Descent [0.03%]
分布式随机 gradient descent 的暂态时间的尖锐估计
Shi Pu,Alex Olshevsky,Ioannis Ch Paschalidis
Shi Pu
This paper is concerned with minimizing the average of n cost functions over a network in which agents may communicate and exchange information with each other. We consider the setting where only noisy gradient information is available. To ...
Identification of Sparse Volterra Systems: An Almost Orthogonal Matching Pursuit Approach [0.03%]
稀疏沃尔泰拉系统的识别：一种近似正交匹配追踪方法
Changming Cheng,Er-Wei Bai,Zhike Peng
Changming Cheng
This paper considers identification of sparse Volterra systems. A method based on the almost orthogonal matching pursuit (AOMP) is proposed. The AOMP algorithm allows one to estimate one non-zero coefficient at a time until all non-zero coe...
Ergodic opinion dynamics over networks: learning influences from partial observations [0.03%]
基于部分观测的学习网络舆论动力学及影响权重
Chiara Ravazzi,Sarah Hojjatinia,Constantino M Lagoa et al.
Chiara Ravazzi et al.
In this paper we address the problem of inferring direct influences in social networks from partial samples of a class of opinion dynamics. The interest is motivated by the study of several complex systems arising in social sciences, where ...