检索结果-内蒙古大学图书馆

Data-Efficient Off-Policy learning for Distributed Optimal Tracking Control of HMAS With Unidentified Exosystem dynamics

引用

ieee TRANSACTIONS ON NEURAL NETWORKS AND learning SYSTEMS 2024年第3期35卷 3181-3190页

作者： Xu, Yong Wu, Zheng-Guang Beijing Inst Technol Sch Automat Beijing 100081 Peoples R China Zhejiang Univ Inst Cyber Syst & Control Hangzhou 310027 Peoples R China

In this article, a data-efficient off-policy reinforcement learning (RL) approach is proposed for distributed output tracking control of heterogeneous multiagent systems (HMASs) using approximate dynamic programming (ADP). Different from existing results that the kinematic model of the exosystem is addressable to partial or all agents, the dynamics of the exosystem are assumed to be completely unknown for all agents in this article. To solve this difficulty, an identifiable algorithm using the experience-replay method is designed for each agent to identify the system matrices of the novel reference model instead of the original exosystem. Then, an output-based distributed adaptive output observer is proposed to provide the estimations of the leader, and the proposed observer not only has a low dimension and less data transmission among agents but also is implemented in a fully distributed way. Besides, a data-efficient RL algorithm is given to design the optimal controller offline along with the system trajectories without solving output regulator equations. An ADP approach is developed to iteratively solve game algebraic Riccati equations (GAREs) using online information of state and input in an online way, which relaxes the requirement of knowing prior knowledge of agents' system matrices in an offline way. Finally, a numerical example is provided to verify the effectiveness of theoretical analysis.

关键词： Heuristic algorithms Observers Mathematical models Approximation algorithms Multi-agent systems Symmetric matrices Regulation adaptive observer approximate dynamic programming (ADP) heterogeneous multiagent systems (HMASs) output tracking reinforcement learning (RL)

来源：评论

学校读者我要写书评

暂无评论

Cybertwin-Driven DRL-Based adaptive Transmission Scheduling for Software Defined Vehicular Networks

引用

ieee TRANSACTIONS ON VEHICULAR TECHNOLOGY 2022年第5期71卷 4607-4619页

作者： Quan, Wei Liu, Mingyuan Cheng, Nan Zhang, Xue Gao, Deyun Zhang, Hongke Beijing Jiaotong Univ Sch Elect & Informat Engn Beijing 100044 Peoples R China Peng Cheng Lab PCL Shenzhen 518040 Peoples R China Xidian Univ State Key Lab ISN Xian 710071 Peoples R China Xidian Univ Sch Telecommun Engn Xian 710071 Peoples R China

Efficient transmission control is a challenging issue in vehicular networks due to the highly dynamic and unpredictable link status. In this paper, we propose a cybertwin-driven learning-based transmission scheduling mechanism for software-defined vehicular networks, which can adaptively select/adjust transmission control methods, i.e., loss-based, delay-based and hybrid ones, to suit to the time-varying network environment. In particular, we first analyze the dynamic network characteristics of three realistic vehicular network scenarios in terms of network throughput, round-trip time (RTT) and RTT jitter. Furthermore, we propose a novel transmission scheduling model and formulate the SDVN transmission scheduling issue as a linear programming problem. To obtain the optimized scheduling policies and guarantee the effectiveness of transmission control, we further propose a Cybertwin-driven and Deep reinforcement learning based transmission control solution (TcpCDRL). Specifically, TcpCDRL is featured with: (i) using deep reinforcement learning (DRL) to adaptively adjust transmission control policy, (ii) using cybertwin-driven transmission controlling to improve the policy-making effectiveness and timeliness. Simulation results show that the proposed TcpCDRL approach outperforms the single well-known transmission control approach (i.e., TcpWestwood, TcpBic, TcpVeno and TcpVegas) in terms of network throughput and RTT.

关键词： reinforcement learning Throughput Reliability Propagation losses Vehicle dynamics Delays Bandwidth Cybertwin-driven deep reinforcement learning adaptive transmission control software defined vehicular networks

来源：评论

学校读者我要写书评

暂无评论

ADHDP(?) Strategies based coordinated ramps metering with queuing consideration

ADHDP(?) Strategies based coordinated ramps metering with qu...

引用

2009 ieee symposium on adaptive dynamic programming and reinforcement learning, ADPRL 2009

作者： Bai, Xuerui Zhao, Dongbin Yi, Jianqiang Laboratory of Complex Systems and Intelligence Science Institute of Automation Chinese Academy of Sciences. 95 Zhongguancun East Road. Haidian District Beijing 100080 China

ISBN: (纸本)9781424427611

Ramp metering has been developed as a traffic management strategy to alleviate congestion on freeways. Most ramp metering control algorithms are concerned without queuing consideration, because it's still a tough job to deal with the problems of coordinated multiple ramps metering with queuing consideration. In this paper, on the basis of our previous studies, we use action-dependent heuristic dynamic programming based on eligibility traces (ADHDP(λ)) to solve local ramp metering and multiple ramps metering problems with queuing consideration. First, for the local ramp metering problem, we establish a comprehensive performance index which considers both traffic density and on-ramp queue length. Second, for the multiple ramps metering problem, based on ADHDP(λ), the coordinated ramps metering and regulating queue lengths are achieved at the same time. Simulation studies on a hypothetical freeway are reported. It is shown that the proposed control scheme is efficient. © 2009 ieee.

关键词： dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Optimization control of UAVs based on self-learning adaptive dynamic programming 35

Optimization control of UAVs based on self-learning adaptive...

引用

35th Youth Academic Annual Conference of Chinese-Association-of-Automation (YAC)

作者： Ye, Shuai Zhou, Ying-Jiang Jiang, Guo-Ping Lin, Qiong Nanjing Univ Posts & Telecommun Dept Automat & Artificial Intelligence Nanjing 210023 Peoples R China

ISBN: (纸本)9781728176840

In UAVs, optimal control has attracted more and more attention. In this paper, a self-learning adaptive dynamic programming (ADP) architecture based reinforcement learning (RL) is proposed to obtain optimal control for UAVs. 1 Compared with the traditional ADP architecture including two networks, one is used to make policy, and the other is used to evaluate policy, We propose to add a third network to replace external reward signals, that is, the agent can acquire reward signals by itself and do not need to interact with the environment. The proposed self-learning ADP method can improve the control performance by online learning while ensuring the state of the system stable at the equilibrium point. Finally, the proposed control algorithm is applied to quadrotor UAVs, and the experimental results show that the effectiveness of the algorithm.

关键词： adaptive dynamic programming Self-learning adaptive dynamic programming reinforcement learning UAVs Online learning

来源：评论

学校读者我要写书评

暂无评论

reinforcement learning of adaptive Longitudinal Vehicle Control for dynamic Collaborative Driving

Reinforcement Learning of Adaptive Longitudinal Vehicle Cont...

引用

ieee Intelligent Vehicles symposium

作者： Ng, Luke Clark, Christopher M. Huissoon, Jan P. Univ Waterloo Dept Mech & Mechatron Engn Waterloo ON N2L 3G1 Canada Calif Polytech State Univ San Luis Obispo Dept Comp Sci San Luis Obispo CA 93407 USA

ISBN: (纸本)9781424425686

dynamic collaborative driving involves the motion coordination of multiple vehicles using shared information from vehicles instrumented to perceive their surroundings in order to improve road usage and safety. A basic requirement of any vehicle participating in dynamic collaborative driving is longitudinal control. Without this capability, higher-level coordination is not possible. This paper focuses on the problem of longitudinal motion control. A detailed nonlinear longitudinal vehicle model which serves as the control system design platform is used to develop a longitudinal adaptive control system based on Monte Carlo reinforcement learning. The results of the reinforcement learning phase and the performance of the adaptive control system for a single automobile as well as the performance in a multi-vehicle platoon is presented.

关键词： adaptive control systems

来源：评论

学校读者我要写书评

暂无评论

adaptive critic-based neurofuzzy controller for the steam generator water level

引用

ieee TRANSACTIONS ON NUCLEAR SCIENCE 2008年第3期55卷 1678-1685页

作者： Fakhrazari, Amin Boroushaki, Mehrdad Sharif Univ Technol Dept Mech Engn Tehran Iran

In this paper, an adaptive critic-based neurofuzzy controller is presented for water level regulation of nuclear steam generators. The problem has been of great concern for many years as the steam generator is a highly nonlinear system showing inverse response dynamics especially at low operating power levels. Fuzzy critic-based learning is a reinforcement learning method based on dynamic programming. The only information available for the critic agent is the system feedback which is interpreted as the last action the controller has performed in the previous state. The signal produced by the critic agent is used alongside the backpropagation of error algorithm to tune online conclusion parts of the fuzzy inference rules. The critic agent here has a proportional-derivative structure and the fuzzy rule base has nine rules. The proposed controller shows satisfactory transient responses, disturbance rejection and robustness to model uncertainty. Its simple design procedure and structure, nominates it as one of the suitable controller designs for the steam generator water level control in nuclear power plant industry.

关键词： adaptive critic-based design fuzzy logic reinforcement learning vertical U-tube steam generator

来源：评论

学校读者我要写书评

暂无评论

Optimal Tracking Current Control of Switched Reluctance Motor Drives Using reinforcement Q-learning Scheduling

引用

ieee ACCESS 2021年 9卷 9926-9936页

作者： Alharkan, Hamad Saadatmand, Sepehr Ferdowsi, Mehdi Shamsi, Pourya Missouri Univ Sci & Technol Elect Engn Dept Rolla MO 65401 USA Qassim Univ Dept Elect Engn Coll Engn Unaizah 56452 Saudi Arabia

In this article, a novel Q-learning scheduling method for the current controller of a switched reluctance motor (SRM) drive is investigated. The Q-learning algorithm is a class of reinforcement learning approaches that can find the best forward-in-time solution of a linear control problem. An augmented system is constructed based on the reference current signal and the SRM model to allow for solving the algebraic Riccati equation of the current-tracking problem. This article introduces a new scheduled-Q-learning algorithm that utilizes a table of Q-cores that lies on the nonlinear surface of an SRM model without involving any information about the model parameters to track the reference current trajectory by scheduling the infinite horizon linear quadratic trackers (LQT) handled by Q-learning algorithms. Additionally, a linear interpolation algorithm is proposed to improve the transition of the LQT between trained Q-cores to ensure a smooth response as state variables evolve on the nonlinear surface of the model. Lastly, simulation and experimental results are provided to validate the effectiveness of the proposed control scheme.

关键词： Mathematical model Adaptation models Rotors Predictive models Current control Trajectory Inductance adaptive dynamic programming current control least square methods motor drive optimal control reinforcement learning switched reluctance motors

来源：评论

学校读者我要写书评

暂无评论

Pseudo-MDPs and factored linear action models

Pseudo-MDPs and factored linear action models

引用

2014 ieee symposium on adaptive dynamic programming and reinforcement learning, ADPRL 2014

作者： Yao, Hengshuai Szepesvári, Csaba Pires, Bernardo Ávila Zhang, Xinhua Department of Computing Science University of Alberta EdmontonABT6G2E8 Canada Machine Learning Research Group National ICT Australia Sydney Australia

ISBN: (纸本)9781479945535

In this paper we introduce the concept of pseudo-MDPs to develop abstractions. Pseudo-MDPs relax the requirement that the transition kernel has to be a probability kernel. We show that the new framework captures many existing abstractions. We also introduce the concept of factored linear action models;a special case. Again, the relation of factored linear action models and existing works are discussed. We use the general framework to develop a theory for bounding the suboptimality of policies derived from pseudo-MDPs. Specializing the framework, we recover existing results. We give a leastsquares approach and a constrained optimization approach of learning the factored linear model as well as efficient computation methods. We demonstrate that the constrained optimization approach gives better performance than the least-squares approach with normalization. © 2014 ieee.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Active learning for personalizing treatment

Active learning for personalizing treatment

引用

ieee symposium on adaptive dynamic programming and reinforcement learning

作者： Deng, Kun Pineau, Joelle Murphy, Susan Department of Statistics University of Michigan United Kingdom Department of Computer Science McGill University Canada

ISBN: (纸本)9781424498888

The personalization of treatment via genetic biomarkers and other risk categories has drawn increasing interest among clinical researchers and scientists. A major challenge here is to construct individualized treatment rules (ITR), which recommend the best treatment for each of the different categories of individuals. In general, ITRs can be constructed using data from clinical trials, however these are generally very costly to run. In order to reduce the cost of learning an ITR, we explore active learning techniques designed to carefully decide whom to recruit, and which treatment to assign, throughout the online conduct of the clinical trial. As an initial investigation, we focus on simple ITRs that utilize a small number of subpopulation categories to personalize treatment. To minimize the maximal uncertainty regarding the treatment effects for each subpopulation, we propose the use of a minimax bandit model and provide an active learning policy for solving it. We evaluate our active learning policy using simulated data and data modeled after a clinical trial involving treatments for depressed individuals. We contrast this policy with other plausible active learning policies. The techniques presented in the paper may be generalized to tackle problems of efficient exploration in other domains. © 2011 ieee.

关键词： Medical applications

来源：评论

学校读者我要写书评

暂无评论

learning Control for Air Conditioning Systems via Human Expressions

引用

ieee TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2021年第8期68卷 7662-7671页

作者： Wei, Qinglai Li, Tao Liu, Derong Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Qingdao Acad Intelligent Ind Qingdao 266109 Peoples R China Guangdong Univ Technol Sch Automat Guangzhou 510006 Peoples R China

In this article, a deep reinforcement learning method is developed to solve air conditioning control problems through human expressions. The main contribution of this article is to design a deep reinforcement learning method for air conditioning control problems with human expressions as the input for the first time. The method aims to eliminate human sleepiness and improve people's work efficiency as much as possible. First, the air conditioning system and deep reinforcement learning methods are introduced. Second, the image processing algorithm for human expressions is described. Third, the deep Q-network method is designed to obtain the optimal control policy for air conditioning systems. Finally, simulation results are given to illustrate the present method that can effectively eliminate sleepiness and improve the work environment of people.

关键词： adaptive dynamic programming air conditioning control deep learning (DL) deep Q-network (DQN) human expressions optimal control reinforcement learning (RL) Q-learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：