检索结果-内蒙古大学图书馆

2015 International Conference on Automation,Mechanical and Electrical Engineering(AMEE 2015)

作者： C.Y.Li X.T.Wang T.W.Zhang School of Computer Science and Technology Harbin University of Science and Technology School of Computer Science and Technology Harbin Institute of Technology

We considered a supply chain inventory scheduling problem in which a central warehouse serves n-retailers under. Mathematical model was developed to obtain the optimal revenue for the proposed policy and the objective function is to minimize revenue per unit time. reinforcement learning algorithm was used to solve the mathematical model, including state determination criteria, reward function, and other parameters. After determining the appropriate parameters of the algorithm, the effectiveness of the algorithm was verified by numerical example. The performance of the algorithm was tested for randomly generated problems. Results show the robust performances of the proposed algorithm.

关键词： Supply chain management one-warehouse multi-retailer problem reinforcement learning algorithm

来源：评论

学校读者我要写书评

暂无评论

A Memory-based reinforcement learning algorithm for Partially Observable Markovian Decision Processes

A Memory-based Reinforcement Learning Algorithm for Partiall...

引用

International Joint Conference on Neural Networks

作者： Zheng, Lei Cho, Siu-Yeung Quek, Chai Nanyang Technol Univ Sch Comp Engn Singapore Singapore

ISBN: (纸本)9781424418206

This paper presents a modified version of U-Tree [1], a memory-based reinforcement learning (RL) algorithm that uses selective perception and short-term memory to handle partially observable Markovian decision processes (POMDP). Conventional RL algorithms rely on a set of pre-defined states to model the environment, even though it can learn the state transitions from experience. U-Tree is not only able to do that, it can also build the state model by itself based on raw sensor inputs. This paper enhances U-Tree's model generation process. The paper also shows that because of the simplified and yet effective state model generated by U-Tree, it is feasible and preferable to adopt the classical Dynamic Programming (DP) algorithm for average reward MDP to solve some difficult POMDP problems. The new U-Tree is tested using a car-driving task with 31,224 world states, with the agent having very limited sensory information and little knowledge about the dynamics of the environment.

关键词： reinforcement learning algorithm Partially Obersvable Markovian Decision Processs Dynamic Programming Average Reward

来源：评论

学校读者我要写书评

暂无评论

Design of Human Resources Management Decision System Based on Multi-Agent System and reinforcement learning algorithm 24

Design of Human Resources Management Decision System Based o...

引用

3rd International Conference on Cyber Security, Artificial Intelligence and Digital Economy (CSAIDE)

作者： Yao, Wenyan Zhang, Tianbao Nanning Univ Nanning 530200 Guangxi Peoples R China Univ Sains Malaysia Sch Management George Town Malaysia Qinzhou Tobacco Monopoly Bur Qinzhou 535000 Guangxi Peoples R China

ISBN: (纸本)9798400718212

This study aims to address the lack of scientific and systematic decision systems in the field of Human Resources Management (HRM). By designing a HRM decision support system based on Multi-Agent systems and reinforcement learning algorithms, effective tools are provided to HR managers to assist them in making more scientific and systematic HRM decisions. The research analyzes the current issues in HRM practices and proposes comprehensive solutions. Through the optimization of Multi-Agent reinforcement learning algorithms, experiments validate the effectiveness of the system in supporting decision-making in HRM. The results demonstrate that the improved algorithms outperform traditional methods, confirming the efficacy of the system's design and optimization. This HRM decision support system, based on Multi-Agent systems and reinforcement learning algorithms, holds the potential to drive organizational development and enhance the efficiency of HRM. However, further research and practical application are needed to refine and optimize the system to adapt to the constantly evolving HRM environment.

关键词： Human Resources Management (HRM) Multi-Agent Systems reinforcement learning algorithm Decision Support System

来源：评论

学校读者我要写书评

暂无评论

Research on Computer Aided learning System Based On reinforcement learning algorithm

引用

Procedia Computer Science 2024年 243卷 472-481页

作者： Haiyan Lu School of Education and Foreign Languages Wuhan Donghu University Wuhan 430212 Hubei China

In today's information-based education era, the computer-aided instruction system under the background of "Internet +" is ushering in unprecedented development opportunities. Based on VARK model, this paper discusses the design and implementation of computer-aided instruction system based on reinforcement learning algorithm. Through in-depth investigation of the application status of computer-aided instruction system and the characteristics of popular systems at home and abroad, combined with the principle and application of reinforcement learning algorithm, this study builds a system architecture with personalized education evaluation function. In the aspect of system design, with the help of neural network model and online test module, the study realizes intelligent analysis and evaluation of students' learning patterns, and improves the pertinence and effect of teaching. Through strict functional and performance tests, the stability and reliability of the system are verified, and the network and intelligent characteristics of the system are demonstrated in the learning process of students, which makes a positive contribution to the improvement of the level of education information and the optimization of teaching effect.

关键词： Computer-Aided Instruction reinforcement learning algorithm VARK Model Intelligent Teaching System

来源：评论

学校读者我要写书评

暂无评论

Construction of Automatic Scheduling and Visualization System for Power Grid Space Operation Based on reinforcement learning algorithm 23

Construction of Automatic Scheduling and Visualization Syste...

引用

Proceedings of the 2023 International Conference on Big Data Mining and Information Processing

作者： Xiaokang Zhu Ning Wang Biao Zou Songtao Zhu Teng Fang Yubo Gao State Grid Electric Power Space Technology Company Limited China

ISBN: (纸本)9798400709166

With the complexity and increasing demand of the power grid, more efficient scheduling methods are needed. reinforcement learning, as an artificial intelligence technology, provides adaptive decision-making solutions that can optimize resource allocation and job scheduling based on the actual state and task requirements of the power grid. The experimental results indicate that the system has achieved significant performance improvement in different power grid operation scenarios. In terms of resource utilization, due to the higher utilization rate of the algorithm in this paper compared to the other two algorithms, the scheduling success rate is correspondingly higher than the other two algorithms. The success rate of the algorithm in this paper can reach 90.24%, which is 22.18% and 22.72% higher than GA (Genetic algorithm) and DL (Deep learning). Finally, in the cost-effectiveness ratio experiment, it is evident that the cost-effectiveness ratio of the algorithm proposed in this paper is much higher than that of the other two algorithms. This demonstrates the potential advantages of reinforcement learning algorithms in power grid spatial job scheduling. Future research can further explore more complex power grid operation and maintenance scenarios and algorithm optimization to continuously improve the efficiency and reliability of power grid operation and maintenance. The construction of an automatic scheduling and visualization system for power grid spatial operations provides strong support for the sustainable development of the power grid industry and the integration of renewable energy.

关键词： Automatic scheduling of power grid operations Optimization of power grid management reinforcement learning algorithm System visualization

来源：评论

学校读者我要写书评

暂无评论

Combination of reinforcement learning and bee algorithm for controlling two-link arm with six muscle: simplified human arm model in the horizontal plane

引用

PHYSICAL AND ENGINEERING SCIENCES IN MEDICINE 2020年第1期43卷 135-142页

作者： Rahatabad, Fereidoun Nowshiravan Rangraz, Parisa Islamic Azad Univ Dept Biomed Engn Sci & Res Branch Tehran Iran

The aim of this study was to improve reinforcement learning algorithm by combining artificial bee colony algorithm. The traditional method of reinforcement learning algorithm has a very low convergence rate due to random choices. An ant algorithm will help to make random choices in reinforcement learning more appropriate. This hybrid algorithm called the bee colony reinforcement (BCR) algorithm. The tip of the arm must reach a predetermined purpose by BCR algorithm. The results show that the BCR algorithm in the model has been able to reduce the time to reach the goal than the reinforcement learning algorithm (In average 12 steps faster). Also, the path for reaching the goal in the BCR algorithm was far more direct and shorter than the reinforcement learning algorithm. This method also detects the optimal path towards the goal.

关键词： reinforcement learning algorithm Human arm modeling Artificial bee colony algorithm Optimization

来源：评论

学校读者我要写书评

暂无评论

Smart Scheduling Strategy for Islanded Microgrid Based on reinforcement learning algorithm

Smart Scheduling Strategy for Islanded Microgrid Based on Re...

引用

上海市研究生“新能源与智能电网”学术论坛

作者： Lingxiao Gan Tao Yu Jing Li Electric Power College South China University of TechnologyGuangzhou 510640China

This paper investigates a hierarchical Automatic Generation Control (AGC) strategy for an islanded microgrid, including wind power, solar photovoltaic, micro turbines, small hydropower and energy storage *** upper AGC is for central *** bottom AGC is to optimize the allocation factors, expecting to meet the requirement of energy-saving generation dispatching (ESGD).Three different bottom controllers are *** of them are designed based on reinforcement learning (RL) *** order to evaluate their control performance, another proportion-based (PROP) controller which has been put into practical application is also *** dynamic models of distributed generations and loads are built to simulate the *** responses to wind turbine hipping and to large load disturbances are *** results indicate that the proposed strategy based on RL algorithm can not only achieve reliability and stability of microgrid in islanded mode, but also reduce fossil energy *** approach is a possible candidate for future microgrid control approaches.

关键词： Distributed generation islanded microgrid hierarchical AGC reinforcement learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Dynamic Coordination of Energy and Hops in WSNs Using reinforcement learning Routing algorithm

Dynamic Coordination of Energy and Hops in WSNs Using Reinfo...

引用

International Conference on Information Sciences,Machinery,Materials and Energy（ICISMME 2015）

作者： Jianyong Li Huang Wei Department of Computer and Information Science Southwest University

In wireless sensor network,the existing reinforcement learning routing algorithm usually optimize single goal and the process of route establishment is *** also has problem of data forwarding control *** this paper,we present a dynamic adaptive routing algorithm with feedback learning ability to balance the energy of wireless sensor network,to reduce the routing hops,and to reduce the establishment *** algorithm will use the local routing information and the method of feedback to learn neighbors' state;routing reward values will be obtained by weighted calculation according to the energy information and the hop counts information;the optimal routing strategy will be obtained by updating the Q-value of routing table.

关键词： Wireless sensor network Routing algorithm reinforcement learning algorithm Energy consumption

来源：评论

学校读者我要写书评

暂无评论

Innovation and Evaluation of Machine Translation Models Combining reinforcement learning algorithms and RNN

引用

Procedia Computer Science 2025年 261卷 821-828页

作者： Ni Xiao School of Public Basic Courses Wuhan Institute of Design and Sciences Wuhan 430205 Hubei China

With the rapid acceleration of global integration, machine translation serves as a crucial conduit for cross - cultural interaction. Nevertheless, the existing conventional models demonstrate insufficient resilience when confronted with texts marred by spelling or grammatical inaccuracies, leading to subpar translation outcomes. In response to this, this study puts forward a novel approach that integrates reinforcement learning algorithms with recurrent neural networks (RNNs) to boost the precision, training velocity, and stability of machine translation. This research melds the reinforcement learning mechanism with recurrent neural networks to enhance the translation precision and adaptability of the model. Experimental findings indicate that the model holds substantial advantages in terms of translation accuracy, training speed, and stability. When compared to the traditional model, the model presented in this paper not only remarkably cuts down the translation error rate to approximately 0.056 but also significantly quickens the training process and exhibits greater stability for diverse input texts. The machine translation model introduced herein skillfully combines the merits of reinforcement learning algorithms and RNNs, effectively surmounting the challenges encountered by traditional machine translation and charting new research directions and practical routes in the domain of machine translation. This innovative accomplishment not only offers robust support for enhancing translation quality but also clears a more unobstructed path for cross - cultural communication.

关键词： reinforcement learning algorithm recurrent neural network machine translation model innovation

来源：评论

学校读者我要写书评

暂无评论

Neural network-based adaptive reinforcement learning for optimized backstepping tracking control of nonlinear systems with input delay

引用

APPLIED INTELLIGENCE 2025年第2期55卷 1-16页

作者： Zhu, Boyan Karimi, Hamid Reza Zhang, Liang Zhao, Xudong Bohai Univ Coll Control Sci & Engn Jinzhou 121013 Liaoning Peoples R China Politecn Milan Dept Mech Engn Via Masa 1 I-20156 Milan Italy DaLian Univ Technol Fac Elect Informat & Elect Engn Dalian 116024 Liaoning Peoples R China

In this paper, the problem of adaptive optimized tracking control design is addressed for a class of nonlinear systems in strict-feedback form. The system under consideration contains input delay and has unmeasurable and restricted states within predefined compact sets. First, neural networks (NNs) are employed to approximate the unknown nonlinear dynamics, and an adaptive neural network (NN) state observer is constructed to compensate for the absence of state information. Additionally, by utilizing an auxiliary system compensation method alongside the backstepping technique, the impact of input delay is eliminated, and the generation of intermediate variables is prevented. Second, tan-type barrier optimal cost functions are established for each subsystem within the backstepping method to prevent the state variables from exceeding preselected sets. Moreover, by establishing both actor and critic NNs to execute a reinforcement learning algorithm, the optimal controller and optimal performance index function are evaluated, while relaxing the persistence of excitation condition. According to the Lyapunov stability theorem, it is demonstrated that all signals in the closed-loop system are semi-globally uniformly ultimately bounded (SGUUB), and the output signal accurately tracks a reference trajectory with the desired precision. Finally, a practical simulation example is provided to verify the effectiveness of the proposed control strategy, demonstrating its potential for real-world implementation.

关键词： reinforcement learning algorithm Auxiliary system State observer Input delay Optimized backstepping technique

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：