Article
Computer Science, Artificial Intelligence
Ziyu Lin, Jingliang Duan, Shengbo Eben Li, Haitong Ma, Jie Li, Jianyu Chen, Bo Cheng, Jun Ma
Summary: The research addresses the challenge of solving the finite-horizon HJB equation, proposes a new algorithm, and validates its effectiveness through simulations.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Automation & Control Systems
Siyu Lv, Jie Xiong
Summary: This paper investigates the optimal impulse control problem in a hybrid diffusion (or regime switching) model, where the system state consists of multiple diffusions coupled by a continuous-time finite-state Markov chain. Based on the dynamic programming principle, the value function of this problem is proven to be the unique viscosity solution to the associated Hamilton-Jacobi-Bellman equation, and a verification theorem is established. Finally, the theoretical results are applied to an optimal cash management problem.
Article
Mathematics, Applied
Wei Wang, Xiangpeng Xie, Changyang Feng
Summary: In this paper, a model-free method based on Q-function is developed to solve the finite-horizon linear quadratic tracking problem. By formulating an augmented system and defining a time-varying Q-function, the solutions of the transformed problem are approximated.
APPLIED MATHEMATICS AND COMPUTATION
(2022)
Article
Automation & Control Systems
Sergio S. Rodrigues
Summary: This article addresses the minimization of energy-like cost functionals in the context of optimal control problems. It shows that a sequence of solutions to finite time-horizon optimal control problems can approximate a solution to the analog infinite time-horizon problem for a general class of dynamical systems, even with possibly unstable and nonlinear free dynamics. The article also presents numerical simulations that validate the theoretical findings for various examples, including systems governed by ordinary and partial differential equations.
SYSTEMS & CONTROL LETTERS
(2023)
Article
Automation & Control Systems
Yichun Li, Shuping Ma
Summary: This paper investigates the indefinite linear quadratic optimal control problem for discrete-time singular Markov jump systems with finite and infinite horizon. Sufficient and necessary conditions are proposed, optimal control and cost values are obtained, and discussion on equivalent transformations and optimal closed-loop systems are provided.
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS
(2021)
Article
Engineering, Mechanical
Guoping Zhang, Quanxin Zhu
Summary: This paper investigates the event-triggered optimal control (ETOC) for nonlinear Ito-type stochastic systems using the adaptive dynamic programming (ADP) approach. The value function of the Hamilton-Jacobi-Bellman (HJB) equation is approximated using critical neural network (CNN), and a new event-triggering scheme is proposed. The Lyapunov direct method is used to prove that the ETOC based on ADP approach guarantees that the CNN weight errors and system states are semi-globally uniformly ultimately bounded in probability.
NONLINEAR DYNAMICS
(2021)
Article
Automation & Control Systems
Ding Wang, Jiangyu Wang, Mingming Zhao, Peng Xin, Junfei Qiao
Summary: This paper presents a novel integrated multi-step heuristic dynamic programming (MsHDP) algorithm for solving optimal control problems. The algorithm, initialized by the zero cost function, is shown to converge to the optimal solution of the Hamilton-Jacobi-Bellman (HJB) equation. The stability of the system is analyzed using control policies generated by MsHDP, and a general stability criterion is designed. Furthermore, an integrated MsHDP algorithm is developed to accelerate learning efficiency by utilizing immature control policies and implementing actor-critic with neural networks.
IEEE-CAA JOURNAL OF AUTOMATICA SINICA
(2023)
Article
Operations Research & Management Science
Yu Guo, Xiao-Bao Shu, Fei Xu, Cheng Yang
Summary: This paper studies the optimal control problem of random impulsive differential equations and solves it by defining a reasonable performance index and obtaining the HJB equation. Through the proof using basic analysis methods and stochastic process theory, the conclusion that the value function satisfies the HJB equation and is its viscosity solution is derived. Additionally, an application example of optimal feedback control is presented.
Article
Automation & Control Systems
Wei Wang, Xin Chen, Jianhua Du
Summary: In this paper, a Q-function-based finite-time control method is introduced to approximate the solutions of the time-varying Riccati equations in the case of unknown system dynamics. The time-varying Q-function and a model-free method are used to represent and approximate the solutions, respectively. Simulation studies validate the effectiveness of the developed method.
INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE
(2023)
Article
Automation & Control Systems
Jeongho Kim, Insoon Yang
Summary: Maximum entropy reinforcement learning methods have been successfully applied to a range of challenging sequential decision-making and control tasks. However, there is a need to extend these methods to continuous-time systems. This article studies the theory of maximum entropy optimal control in continuous time and derives a novel class of equations. The results demonstrate the performance of the maximum entropy method in continuous-time optimal control and reinforcement learning problems.
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
(2023)
Article
Engineering, Multidisciplinary
Yunxiao Ren, Qishao Wang, Zhisheng Duan
Summary: In this article, a novel neural network-based integrated heuristic dynamic programming algorithm is proposed to solve the optimal leader-following consensus control problem of multi-agent systems under a distributed learning framework. The algorithm combines policy iteration and value iteration methods to achieve the Nash equilibrium of performance index among agents. Neural network approximation is used to handle the unknown structures of the local value functions of agents.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2022)
Article
Automation & Control Systems
Zengjing Chen, Xinwei Feng, Shuhui Liu, Weihai Zhang
Summary: This paper applies the method of backward stochastic differential equations (BSDEs) to study the bang-bang optimal stochastic control problem, and provides the existence, explicit representation, and explicit solution of nonlinear BSDEs with symmetric terminal condition for the optimal control and the optimal value function.
Article
Mathematics, Applied
Karl Kunisch, Donato Vasquez-Varas
Summary: This article analyzes a learning technique for finite horizon optimal control problems and its approximation based on polynomials, and illustrates the practicality and efficiency of the method.
COMPUTERS & MATHEMATICS WITH APPLICATIONS
(2023)
Article
Engineering, Chemical
Tianpeng Fan, Zhengtao Ding
Summary: This paper investigates the optimal control of a switched nonlinear system with multiple subsystems and different dynamics. The goal is to minimize the cost function by establishing a switching law that determines the sequence of subsystems, switching time, and control input. The HJB equation for the switched system is derived, and Galerkin's spectral method is introduced for approximation. A numerical example of a continuous stirred tank reactor demonstrates the effectiveness of the proposed method in improving system performance. This paper is the first attempt to investigate the optimal control of switched CSTR systems.
CHEMICAL ENGINEERING SCIENCE
(2023)
Article
Automation & Control Systems
Qinglai Wei, Liao Zhu, Tao Li, Derong Liu
Summary: This article develops a new time-varying adaptive dynamic programming (ADP) algorithm to solve finite-horizon optimal control problems for a class of discrete-time affine nonlinear systems. Inspired by the pseudolinear method, the nonlinear system can be approximated by a series of time-varying linear systems. The paper proves the convergence of the states of the time-varying linear systems to the states of the discrete-time affine nonlinear systems and the convergence of the iterative value functions and control laws to the optimal ones. Numerical results are provided to verify the effectiveness of the proposed method.
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
(2022)
Article
Computer Science, Artificial Intelligence
Rui Lv, Dingheng Wang, Jiangbin Zheng, Zhao-Xu Yang
Summary: In this paper, the authors investigate tensor decomposition for neural network compression. They analyze the convergence and precision of tensor mapping theory, validate the rationality of tensor mapping and its superiority over traditional tensor approximation based on the Lottery Ticket Hypothesis. They propose an efficient method called 3D-KCPNet to compress 3D convolutional neural networks using the Kronecker canonical polyadic (KCP) tensor decomposition. Experimental results show that 3D-KCPNet achieves higher accuracy compared to the original baseline model and the corresponding tensor approximation model.
Article
Computer Science, Artificial Intelligence
Xiangkun He, Zhongxu Hu, Haohan Yang, Chen Lv
Summary: In this paper, a novel constrained multi-objective reinforcement learning algorithm is proposed for personalized end-to-end robotic control with continuous actions. The approach trains a single model using constraint design and a comprehensive index to achieve optimal policies based on user-specified preferences.
Article
Computer Science, Artificial Intelligence
Zhijian Zhuo, Bilian Chen, Shenbao Yu, Langcai Cao
Summary: In this paper, a novel method called Expansion with Contraction Method for Overlapping Community Detection (ECOCD) is proposed, which utilizes non-negative matrix factorization to obtain disjoint communities and applies expansion and contraction processes to adjust the degree of overlap. ECOCD is applicable to various networks with different properties and achieves high-quality overlapping community detection.
Article
Computer Science, Artificial Intelligence
Yizhe Zhu, Chunhui Zhang, Jialin Gao, Xin Sun, Zihan Rui, Xi Zhou
Summary: In this work, the authors propose a Contrastive Spatio-Temporal Distilling (CSTD) approach to improve the detection of high-compressed deepfake videos. The approach leverages spatial-frequency cues and temporal-contrastive alignment to fully exploit spatiotemporal inconsistency information.
Review
Computer Science, Artificial Intelligence
Laijin Meng, Xinghao Jiang, Tanfeng Sun
Summary: This paper provides a review of coverless steganographic algorithms, including the development process, known contributions, and general issues in image and video algorithms. It also discusses the security of coverless steganography from theoretical analysis to actual investigation for the first time.
Article
Computer Science, Artificial Intelligence
Yajie Bao, Tianwei Xing, Xun Chen
Summary: Visual question answering requires processing multi-modal information and effective reasoning. Neural-symbolic learning is a promising method, but current approaches lack uncertainty handling and can only provide a single answer. To address this, we propose a confidence based neural-symbolic approach that evaluates NN inferences and conducts reasoning based on confidence.
Article
Computer Science, Artificial Intelligence
Anh H. Vo, Bao T. Nguyen
Summary: Interior style classification is an interesting problem with potential applications in both commercial and academic domains. This project proposes a method named ISC-DeIT, which combines data-efficient image transformer architectures and knowledge distillation, to address the interior style classification problem. Experimental results demonstrate a significant improvement in predictive accuracy compared to other state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Shashank Kotyan, Danilo Vasconcellos Vargas
Summary: This article introduces a novel augmentation technique called Dynamic Scanning Augmentation to improve the accuracy and robustness of Vision Transformer (ViT). The technique leverages dynamic input sequences to adaptively focus on different patches, resulting in significant changes in ViT's attention mechanism. Experimental results demonstrate that Dynamic Scanning Augmentation outperforms ViT in terms of both robustness to adversarial attacks and accuracy against natural images.
Article
Computer Science, Artificial Intelligence
Hiba Alqasir, Damien Muselet, Christophe Ducottet
Summary: The article proposes a solution to improve the learning process of a classification network by providing shape priors, reducing the need for annotated data. The solution is tested on cross-domain digit classification tasks and a video surveillance application.
Article
Computer Science, Artificial Intelligence
Dexiu Ma, Mei Liu, Mingsheng Shang
Summary: This paper proposes a method using neural dynamics solvers to solve infinity-norm optimization problems. Two improved solvers are constructed and their effectiveness and superiority are demonstrated through theoretical analysis and simulation experiments.
Article
Computer Science, Artificial Intelligence
Francesco Gregoretti, Giovanni Pezzulo, Domenico Maisto
Summary: Active Inference is a computational framework that uses probabilistic inference and variational free energy minimization to describe perception, planning, and action. cpp-AIF is a header-only C++ library that provides a powerful tool for implementing Active Inference for Partially Observable Markov Decision Processes through multi-core computing. It is cross-platform and improves performance, memory management, and usability compared to existing software.
Article
Computer Science, Artificial Intelligence
Zelin Ying, Dawei Cheng, Cen Chen, Xiang Li, Peng Zhu, Yifeng Luo, Yuqi Liang
Summary: This paper proposes a novel stock market trends prediction framework called SMART, which includes a self-supervised stock technical data sequence embedding model S3E. By training with multiple self-supervised auxiliary tasks, the model encodes stock technical data sequences into embeddings and uses the learned sequence embeddings for predicting stock market trends. Extensive experiments on China A-Shares market and NASDAQ market prove the high effectiveness of our model in stock market trends prediction, and its effectiveness is further validated in real-world applications in a leading financial service provider in China.
Article
Computer Science, Artificial Intelligence
Hao Li, Hao Jiang, Dongsheng Ye, Qiang Wang, Liang Du, Yuanyuan Zeng, Liu Yuan, Yingxue Wang, C. Chen
Summary: DHGAT1, a dynamic hyperbolic graph attention network, utilizes hyperbolic metric properties to embed dynamic graphs. It employs a spatiotemporal self-attention mechanism and weighted node representations, resulting in excellent performance in link prediction tasks.
Article
Computer Science, Artificial Intelligence
Jiehui Huang, Zhenchao Tang, Xuedong He, Jun Zhou, Defeng Zhou, Calvin Yu-Chian Chen
Summary: This study proposes a progressive learning multi-scale feature blending model for image deraining tasks. The model utilizes detail dilation and texture extraction to improve the restoration of rainy images. Experimental results show that the model achieves near state-of-the-art performance in rain removal tasks and exhibits better rain removal realism.
Article
Computer Science, Artificial Intelligence
Lizhi Liu, Zilin Gao, Yinhe Wang, Yongfu Li
Summary: This paper proposes a novel discrete-time interconnected model for depicting complex dynamical networks. The model consists of nodes and edges subsystems, which consider the dynamic characteristic of both nodes and edges. By designing control strategies and coupling modes, the stabilization and synchronization of the network are achieved. Simulation results demonstrate the effectiveness of the proposed methods.