期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到246,333篇文章
< 1 2 … 250 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
Intelligent Ridge Path Planning for Agriculture Robot Using Modified Q-Learning Algorithm 认领 引用
1
作者 A.Sivasangari V.J.K.Kishor Sonti +3 位作者 J.Cruz Antony E.Murali D.Deepa A.Happonen 《Computers, Materials & Continua》 SCIE EI 2026年第6期1613-1636,共24页
In the past two decades,Precision Agriculture has received research attention since the development of robotics.Agricultural robotic equipment and drones,which can be operated by farmers,are appearing more frequently ... In the past two decades,Precision Agriculture has received research attention since the development of robotics.Agricultural robotic equipment and drones,which can be operated by farmers,are appearing more frequently and being used to make the process of farming easier and more productive.This paper attempts to develop a modified Q-learning algorithm.A reinforcement learning algorithm called Q-learning has Q-values that are updated in order to find the best routes for the robotic devices to follow while avoiding any obstacles.Different types of terrain and other factors that influence the development of good routes for the robotic devices are included in the experiments performed.Through an extensive set of experiments done with different types of terrain the researchers found that the modified Q-learning algorithm converges to the optimal path significantly quicker than the current benchmark Deep Q-Network(DQN)algorithms and that the average distance that the modified Q-learning algorithm travels to get to its destination over different terrane types was 28.7%shorter than the average distance traveled using the standard DQNs.The researchers also found that the modified Q-learning algorithm has been able to successfully avoid obstacles on 99.5%of all occasions tested.The shortest route to the destination is expected to take less time,and it demonstrates the benefit of using a robotic device that has the ability to detect and avoid obstacles in order to be effective on more difficult types of terrain. 展开更多
关键词 Path planning agricultural robotics reinforcement learning Q-learning
暂未订购 下载PDF
Antenna Selection in Energy Harvesting Relaying Networks Using Q-Learning Algorithm 认领 引用 被引量：1
2
作者 Daliang Ouyang Rui Zhao +2 位作者 Yuanjian Li Rongxin Guo Yi Wang 《China Communications》 SCIE EI CSCD 2021年第4期64-75,共12页
In this paper,a novel opportunistic scheduling(OS)scheme with antenna selection(AS)for the energy harvesting(EH)cooperative communication system where the relay can harvest energy from the source transmission is propo... In this paper,a novel opportunistic scheduling(OS)scheme with antenna selection(AS)for the energy harvesting(EH)cooperative communication system where the relay can harvest energy from the source transmission is proposed.In this considered scheme,we take into both traditional mathematical analysis and reinforcement learning(RL)scenarios with the power splitting(PS)factor constraint.For the case of traditional mathematical analysis of a fixed-PS factor,we derive an exact closed-form expressions for the ergodic capacity and outage probability in general signal-to-noise ratio(SNR)regime.Then,we combine the optimal PS factor with performance metrics to achieve the optimal transmission performance.Subsequently,based on the optimized PS factor,a RL technique called as Q-learning(QL)algorithm is proposed to derive the optimal antenna selection strategy.To highlight the performance advantage of the proposed QL with training the received SNR at the destination,we also examine the scenario of QL scheme with training channel between the relay and the destination.The results illustrate that,the optimized scheme is always superior to the fixed-PS factor scheme.In addition,a better system parameter setting with QL significantly outperforms the traditional mathematical analysis scheme. 展开更多
关键词 Q-learning optimal PS factor outage probability ergodic capacity antenna selection
暂未订购 下载PDF
Bayes-Q-Learning Algorithm in Edge Computing for Waste Tracking 认领 引用
3
作者 D.Palanikkumar R.Ramesh Kumar +2 位作者 Mehedi Masud Mrim M.Alnfiai Mohamed Abouhawwash 《Intelligent Automation & Soft Computing》 SCIE 2023年第5期2425-2440,共16页
The major environmental hazard in this pandemic is the unhygienic dis-posal of medical waste.Medical wastage is not properly managed it will become a hazard to the environment and humans.Managing medical wastage is a ... The major environmental hazard in this pandemic is the unhygienic dis-posal of medical waste.Medical wastage is not properly managed it will become a hazard to the environment and humans.Managing medical wastage is a major issue in the city,municipalities in the aspects of the environment,and logistics.An efficient supply chain with edge computing technology is used in managing medical waste.The supply chain operations include processing of waste collec-tion,transportation,and disposal of waste.Many research works have been applied to improve the management of wastage.The main issues in the existing techniques are ineffective and expensive and centralized edge computing which leads to failure in providing security,trustworthiness,and transparency.To over-come these issues,in this paper we implement an efficient Naive Bayes classifier algorithm and Q-Learning algorithm in decentralized edge computing technology with a binary bat optimization algorithm(NBQ-BBOA).This proposed work is used to track,detect,and manage medical waste.To minimize the transferring cost of medical wastage from various nodes,the Q-Learning algorithm is used.The accuracy obtained for the Naïve Bayes algorithm is 88%,the Q-Learning algo-rithm is 82%and NBQ-BBOA is 98%.The error rate of Root Mean Square Error(RMSE)and Mean Error(MAE)for the proposed work NBQ-BBOA are 0.012 and 0.045. 展开更多
关键词 Binary bat algorithm naïve bayes supply chain edge medical wastage
暂未订购 下载PDF
Multi-agent reinforcement learning using modular neural network Q-learning algorithms 认领 引用
4
作者 杨银贤 《Journal of Chongqing University》 2005年第1期50-54,共5页
Reinforcement learning is an excellent approach which is used in artificial intelligence,automatic control, etc. However, ordinary reinforcement learning algorithm, such as Q-learning with lookup table cannot cope wit... Reinforcement learning is an excellent approach which is used in artificial intelligence,automatic control, etc. However, ordinary reinforcement learning algorithm, such as Q-learning with lookup table cannot cope with extremely complex and dynamic environment due to the huge state space. To reduce the state space, modular neural network Q-learning algorithm is proposed, which combines Q-learning algorithm with neural network and module method. Forward feedback neural network, Elman neural network and radius-basis neural network are separately employed to construct such algorithm. It is revealed that Elman neural network Q-learning algorithm has the best performance under the condition that the same neural network training method, i.e. gradient descent error back-propagation algorithm is applied. 展开更多
关键词 reinforcement learning Q-learning neural network artificial intelligence
暂未订购 下载PDF
Double BP Q-Learning Algorithm for Local Path Planning of Mobile Robot 认领 引用 被引量：2
5
作者 Guoming Liu Caihong Li +2 位作者 Tengteng Gao Yongdi Li Xiaopei He 《Journal of Computer and Communications》 2021年第6期138-157,共20页
Aiming at the dimension disaster problem, poor model generalization ability and deadlock problem in special obstacles environment caused by the increase of state information in the local path planning process of mobil... Aiming at the dimension disaster problem, poor model generalization ability and deadlock problem in special obstacles environment caused by the increase of state information in the local path planning process of mobile robot, this paper proposed a Double BP Q-learning algorithm based on the fusion of Double Q-learning algorithm and BP neural network. In order to solve the dimensional disaster problem, two BP neural network fitting value functions with the same network structure were used to replace the two Q value tables in Double Q-Learning algorithm to solve the problem that the Q value table cannot store excessive state information. By adding the mechanism of priority experience replay and using the parameter transfer to initialize the model parameters in different environments, it could accelerate the convergence rate of the algorithm, improve the learning efficiency and the generalization ability of the model. By designing specific action selection strategy in special environment, the deadlock state could be avoided and the mobile robot could reach the target point. Finally, the designed Double BP Q-learning algorithm was simulated and verified, and the probability of mobile robot reaching the target point in the parameter update process was compared with the Double Q-learning algorithm under the same condition of the planned path length. The results showed that the model trained by the improved Double BP Q-learning algorithm had a higher success rate in finding the optimal or sub-optimal path in the dense discrete environment, besides, it had stronger model generalization ability, fewer redundant sections, and could reach the target point without entering the deadlock zone in the special obstacles environment. 展开更多
关键词 Mobile Robot Local Path Planning Double BP Q-Learning BP Neural Network Transfer Learning
暂未订购 下载PDF
Hyper-heuristic Evolutionary Algorithm Utilizing Q-learning for Addressing the Distributed Flexible Job-Shop Scheduling Problem in the Context of Worker Absenteeism 认领 引用
6
作者 Zhiqing Li Yongquan Zhou Qifang Luo 《Journal of Bionic Engineering》 SCIE EI CSCD 2026年第3期1932-1969,共38页
The Distributed Flexible Job Shop Scheduling Problem(DFJSP)is critical in modern manufacturing;however,existing research has not sufficiently addressed dynamic disturbances,particularly unexpected worker absences.This... The Distributed Flexible Job Shop Scheduling Problem(DFJSP)is critical in modern manufacturing;however,existing research has not sufficiently addressed dynamic disturbances,particularly unexpected worker absences.This study extends the DFJSPW model to introduce an enhanced framework,DFJSPWA,which optimizes maximum makespan,worker workload,and total energy consumption by integrating worker load factors with random absenteeism.To solve this complex problem,we propose a Q-learning-based Hyper-heuristic Evolutionary Algorithm(QLHHEA).This algorithm features a segmented encoding scheme that implicitly captures absenteeism information,utilizing a decoding process tailored for both standard and rescheduling contexts.Additionally,we construct a pool of twelve efficient Low-Level Heuristics(LLHs)combined with Q-learning to enable the adaptive selection of operators.Furthermore,a Hybrid Rescheduling Method(HRM)is developed,employing three response strategies based on worker status and the urgency of the absenteeism.Comprehensive experiments on 58 benchmark instances demonstrate that QLHHEA significantly outperforms six established algorithms,including MOEA/D and NSGA-II.Statistical validation confirms the superiority of the proposed method.This research provides a robust theoretical and methodological framework for improving scheduling efficiency and resource utilization in distributed production systems facing worker absenteeism. 展开更多
关键词 Worker absenteeism Distributed flexible job shop scheduling problem Hyper-heuristic evolutionary algorithm Dynamic rescheduling Q-learning
Dynamic Integration of Q-Learning and A-APF for Efficient Path Planning in Complex Underground Mining Environments 认领 引用 被引量：1
7
作者 Chang Su Liangliang Zhao Dongbing Xiang 《Computers, Materials & Continua》 SCIE EI 2026年第2期1017-1040,共24页
To address low learning efficiency and inadequate path safety in spraying robot navigation within complex obstacle-rich environments—with dense,dynamic,unpredictable obstacles challenging conventional methods—this p... To address low learning efficiency and inadequate path safety in spraying robot navigation within complex obstacle-rich environments—with dense,dynamic,unpredictable obstacles challenging conventional methods—this paper proposes a hybrid algorithm integrating Q-learning and improved A*-Artificial Potential Field(A-APF).Centered on theQ-learning framework,the algorithmleverages safety-oriented guidance generated byA-APF and employs a dynamic coordination mechanism that adaptively balances exploration and exploitation.The proposed system comprises four core modules:(1)an environment modeling module that constructs grid-based obstacle maps;(2)an A-APF module that combines heuristic search from A*algorithm with repulsive force strategies from APF to generate guidance;(3)a Q-learning module that learns optimal state-action values(Q-values)through spraying robot-environment interaction and a reward function emphasizing path optimality and safety;and(4)a dynamic optimization module that ensures adaptive cooperation between Q-learning and A-APF through exploration rate control and environment-aware constraints.Simulation results demonstrate that the proposed method significantly enhances path safety in complex underground mining environments.Quantitative results indicate that,compared to the traditional Q-learning algorithm,the proposed method shortens training time by 42.95% and achieves a reduction in training failures from 78 to just 3.Compared to the static fusion algorithm,it further reduces both training time(by 10.78%)and training failures(by 50%),thereby improving overall training efficiency. 展开更多
关键词 Q-learning A*algorithm artificial potential field path planning hybrid algorithm
暂未订购 下载PDF
基于随机森林与Q-learning融合的多元电力数据存储优化决策方法 认领 引用
8
作者 叶学顺 贾东梨 +2 位作者 周俊 唐英 贾梓豪 《科学技术与工程》 EI 北大核心 2026年第3期1065-1074,共10页
大规模和多样的电力数据存储面临效率低和内存容量不足的瓶颈问题。数据索引和数据压缩等传统数据存储优化方法各有优劣势,如何有效应用于电力数据存储是目前研究的难点。为了解决这个问题,提出了一种融合随机森林和Q-learning的多元电... 大规模和多样的电力数据存储面临效率低和内存容量不足的瓶颈问题。数据索引和数据压缩等传统数据存储优化方法各有优劣势,如何有效应用于电力数据存储是目前研究的难点。为了解决这个问题,提出了一种融合随机森林和Q-learning的多元电力数据存储优化决策方法。该方法中的关键技术包括:首先提出了基于改进随机森林算法的存储优化策略决策模型,引入信息增益方法,综合评价数据存储时对数据库的数据访问频率、查询时间、存储速度以及数据冗余率等因素影响,做出数据直接存储、数据索引存储和数据压缩存储的存储优化方法策略决策;其次提出了基于改进Q-learning算法的数据存储算法决策模型,引入多尺度学习机制、优先经验放回机制和正负向奖励机制,决策数据索引存储时适用的索引算法以及数据压缩存储时适用的数据压缩算法。本方法有效融合了数据索引与数据压缩的技术优势,大幅提升数据存储效率并节约存储空间,为大规模多元电力数据管理提供新的解决方案。 展开更多
关键词 随机森林算法 Q-learning算法 数据存储优化方法 数据索引算法 数据压缩算法
暂未订购 下载PDF
基于Q-Learning的多模态自适应光伏功率优化组合预测 认领 引用
9
作者 隗知初 杨苹 +3 位作者 周钱雨凡 陈文皓 万思洋 崔嘉雁 《电力工程技术》 CSCD 北大核心 2026年第1期115-124,163,共10页
针对光伏功率序列波动性强、随机性高的问题,文中提出一种基于Q-Learning的多模态自适应光伏功率优化组合预测模型。首先,采用鲸鱼优化算法的变分模态分解方法,将原始光伏功率序列分解成不同子模态,并通过集成特征筛选模型,确定各子模... 针对光伏功率序列波动性强、随机性高的问题,文中提出一种基于Q-Learning的多模态自适应光伏功率优化组合预测模型。首先,采用鲸鱼优化算法的变分模态分解方法,将原始光伏功率序列分解成不同子模态,并通过集成特征筛选模型,确定各子模态序列最敏感的气象因素。然后,构建反向传播神经网络、双向长短期记忆网络、门控循环单元网络和时间卷积网络4种基础预测模型。考虑到不同模型对不同频率特征的子序列预测能力不同,利用Q-Learning算法自适应选择各模态对应的最优基础模型组合方式。最后,将不同子模态的预测结果叠加重构,得到最终预测结果,并利用高分辨率光伏气象功率数据集进行验证。结果证明,文中所提出的基于Q-Learning的多模态自适应光伏功率优化组合预测模型,相较于单一模型的预测误差平均绝对误差下降了16.18%,均方误差下降了17.00%。 展开更多
关键词 鲸鱼优化算法 变分模态分解 Q-Learning 功率预测 组合模型 光伏发电
暂未订购 下载PDF
基于Q-learning的零等待作业车间调度优化 认领 引用
10
作者 王海林 吴瑶 +1 位作者 张刚 夏霖辉 《计算机应用与软件》 北大核心 2026年第5期252-257,286,共6页
针对以拖期时间最小为目标的零等待作业车间调度问题,提出基于强化学习中的Q-learning算法的求解方法。根据问题结构和目标函数特点,设计状态空间、奖励函数和四种调度规则(LOR、LWR、MOR、MWR)组成的动作集合,根据系统状态采用ε-贪婪... 针对以拖期时间最小为目标的零等待作业车间调度问题,提出基于强化学习中的Q-learning算法的求解方法。根据问题结构和目标函数特点,设计状态空间、奖励函数和四种调度规则(LOR、LWR、MOR、MWR)组成的动作集合,根据系统状态采用ε-贪婪策略选取调度规则,使状态-动作值函数迭代收敛于最优值。大量算例的实验结果表明,所提出的Q-learning算法求得的方案优于使用单一调度规则所生成的调度结果。 展开更多
关键词 零等待作业车间调度 强化学习 Q-learning算法 调度规则
暂未订购 下载PDF
锅炉汽轮机系统经验导向单评价Q-learning负荷控制 认领 引用
11
作者 刘晓敏 余梦君 +3 位作者 王浩宇 杨春雨 周林娜 周怀春 《控制理论与应用》 EI CAS CSCD 北大核心 2026年第5期1034-1042,共9页
为解决锅炉-汽轮机系统负荷控制面临的精准数学模型难以构建、阀门约束呈现非对称特性和运行经验数据抽取方法单一等挑战,本文提出一种基于经验导向单评价Q-learning算法的锅炉-汽轮机系统自适应负荷跟踪控制方法.引入约束转换函数,将... 为解决锅炉-汽轮机系统负荷控制面临的精准数学模型难以构建、阀门约束呈现非对称特性和运行经验数据抽取方法单一等挑战,本文提出一种基于经验导向单评价Q-learning算法的锅炉-汽轮机系统自适应负荷跟踪控制方法.引入约束转换函数,将约束非对称输入映射至控制范围的中值,处理非对称问题,并将性能指标函数重塑为不含额外惩罚项的形式.为降低在线计算负荷,提出轻量型单评价网络Q-learning算法,实现对改进后性能指标函数的快速学习.利用前幕更新所得策略在多幕数据之间在线建立经验导向关系,搭建多幕分段训练新模式,实现数据高效挖掘,加快算法收敛速度.通过在160 MW锅炉-汽轮机系统仿真,验证所提出控制算法的有效性和优越性. 展开更多
关键词 锅炉-汽轮机系统 经验导向 单评价网络 Q-learning 负荷跟踪
暂未订购 下载PDF
基于Q-learning的专家权重优化与多级共识反馈决策 认领 引用
12
作者 杜秀丽 程伟龙 +2 位作者 高星 潘成胜 吕亚娜 《计算机应用研究》 CSCD 北大核心 2026年第2期420-426,共7页
针对动态复杂多属性决策环境下大规模异构专家群体共识达成效率低、权重分配不精准的问题,提出一种基于Q-learning的权重优化与多级共识反馈方法,旨在提升共识水平与决策质量。该方法通过将专家权重动态调整建模为马尔可夫决策过程,利用... 针对动态复杂多属性决策环境下大规模异构专家群体共识达成效率低、权重分配不精准的问题,提出一种基于Q-learning的权重优化与多级共识反馈方法,旨在提升共识水平与决策质量。该方法通过将专家权重动态调整建模为马尔可夫决策过程,利用Q-learning实现权重自适应优化,并设计涵盖属性、方案、专家与群体四个层级的多级共识反馈机制,从而精准识别并协调不同来源的分歧。实验结果表明,该方法能够显著降低共识达成所需迭代次数,提升权重分配与专家专业度的匹配精度,并获得更可靠的方案排序结果,验证了其在大规模异构专家群体中的鲁棒性与计算效率。研究表明,所提方法为复杂多属性群体决策问题提供了有效的共识建模与决策支持工具。 展开更多
关键词 群体决策 Q-learning 多层共识反馈 动态权重调整
暂未订购 下载PDF
Real-Time Optimization of Vertical Roller Mills Using XGBoost Prediction and Q-Learning Control 认领 引用
13
作者 Anping Wan Yingchang Gao +2 位作者 Weikang Liu Rui Yin Khalil Al-Bukhaiti 《Computers, Materials & Continua》 SCIE EI 2026年第8期1515-1534,共20页
Vertical roller mills are essential for energy-intensive grinding in cement,minerals,and metallurgy industries,consuming up to 50%of plant electricity and frequently experiencing operational instabilities(including ex... Vertical roller mills are essential for energy-intensive grinding in cement,minerals,and metallurgy industries,consuming up to 50%of plant electricity and frequently experiencing operational instabilities(including excessive vibration and main motor current fluctuations)that drive unplanned downtime,increased wear,and reduced throughput.Despite their importance,real-time autonomous optimization remains challenging due to the nonlinear interactions among grinding pressure,feed rate,separator speed,and aerodynamic factors,which limit traditional control strategies under varying loads.This paper presents a real-time operational optimization system for large-scale vertical roller mills using big industrial data and artificial intelligence(AI).From a 5400 kW Loesche LM56.4 mill,2,764,800 samples were collected at 1 Hz over 32 days of continuous production.A systematic pipeline was developed:quartile-based outlier-robust cleaning;domain-informed feature engineering including Total Current;Random Forest(RF)permutation importance selection of the top 15 parameters;and Extreme Gradient Boosting(XGBoost)regression models with hyperparameters tuned by Tree-structured Parzen Estimator(TPE)Bayesian optimization.The resulting models achieved strong predictive performance,Mean Absolute Percentage Error(MAPE)of 1.3%(95%CI:1.1%–1.5%)for main motor current(R2=0.9997)and 5.8%(95%CI:5.3%–6.3%)for shell vibration(R2=0.9717),representing reductions of 89%and 59%,respectively,relative to the Long Short-Term Memory(LSTM)baseline.These surrogates were embedded into a tabular Q-learning Reinforcement Learning(RL)agent that autonomously adjusts feed rate,grinding pressure,separator speed,and exhaust damper position via a discrete action space and multi-objective reward function,communicating with the Distributed Control System(DCS)via Open Platform Communications Unified Architecture(OPC-UA).Closed-loop evaluation yielded simultaneous reductions of 6.0%in peak current(181.92→170.04 A)and 9.4%in peak vibration(5.51→4.99 mm/s)while maintaining throughput.A PyQt5-based graphical interface enabling real-time monitoring,predictive alerts,and automatic DCS write-back was deployed and operated stably for two weeks. 展开更多
关键词 Vertical roller mill operational optimization XGBoost Bayesian hyperparameter optimization Q-learning energy efficiency vibration reduction real-time control Industry 4.0
暂未订购 下载PDF
考虑极地气象的改进Q-Learning船舶航线规划算法 认领 引用
14
作者 赵玉新 陈博睿 +1 位作者 赵恩娇 胡百川 《中国惯性技术学报》 EI CSCD 北大核心 2026年第6期618-626,共9页
为了解决船舶在范围宽广的极地环境使用Q-Learning进行航线规划时求解速度慢的问题,提出一种结合人工势场法的改进Q-Learning算法。首先,针对传统Q-Learning算法探索盲目性大的问题,结合极地的冰情、气象等要素,在单步奖励函数Reward中... 为了解决船舶在范围宽广的极地环境使用Q-Learning进行航线规划时求解速度慢的问题,提出一种结合人工势场法的改进Q-Learning算法。首先,针对传统Q-Learning算法探索盲目性大的问题,结合极地的冰情、气象等要素,在单步奖励函数Reward中引入目标点对船舶的吸引势场、海冰区和陆地对船舶的排斥势场以及风力势场;再者,为加快算法收敛速度,引入随迭代次数而变化的贪婪系数;最后,为解决维度爆炸问题,采用低分辨率总体规划加高分辨率分段规划的规划方案。实验结果表明,与传统Q-Learning算法相比,改进算法可灵活应对极地复杂环境,求解速度可提高6倍以上,线路长度缩短84%以上,顺风指数提升45%以上。 展开更多
关键词 极地船舶 极地气象 Q-Learning 人工势场法 航线规划
暂未订购 下载PDF
Adaptive Path-Planning for Autonomous Robots:A UCH-Enhanced Q-Learning Approach 认领 引用
15
作者 Wei Liu Ruiyang Wang Guangwei Liu 《Computers, Materials & Continua》 SCIE EI 2026年第2期731-753,共23页
Q-learning is a classical reinforcement learning method with broad applicability.It can respond effectively to environmental changes and provide flexible strategies,making it suitable for solving robot path-planning p... Q-learning is a classical reinforcement learning method with broad applicability.It can respond effectively to environmental changes and provide flexible strategies,making it suitable for solving robot path-planning problems.However,Q-learning faces challenges in search and update efficiency.To address these issues,we propose an improved Q-learning(IQL)algorithm.We use an enhanced Ant Colony Optimization(ACO)algorithmto optimizeQtable initialization.We also introduce the UCH mechanism to refine the reward function and overcome the exploration dilemma.The IQL algorithm is extensively tested in three grid environments of different scales.The results validate the accuracy of themethod and demonstrate superior path-planning performance compared to traditional approaches.The algorithm reduces the number of trials required for convergence,improves learning efficiency,and enables faster adaptation to environmental changes.It also enhances stability and accuracy by reducing the standard deviation of trials to zero.On grid maps of different sizes,IQL achieves higher expected returns.Compared with the original Q-learning algorithm,IQL improves performance by 12.95%,18.28%,and 7.98% on 10*10,20*20,and 30*30 maps,respectively.The proposed algorithm has promising applications in robotics,path planning,intelligent transportation,aerospace,and game development. 展开更多
关键词 Path planning IQL algorithms UCH mechanism
暂未订购 下载PDF
基于Q-Learning的智能座舱自适应多模态融合控制方法研究 认领 引用
16
作者 王文冲 刘海月 +2 位作者 张强 王川宿 张鸥 《时代汽车》 2026年第8期103-107,共5页
针对智能座舱多模态交互系统在复杂的驾驶场景中出现的适应性、鲁棒性不足的问题,文章采用Q-Learning强化学习算法来实现自适应多模态融合控制。首先,对智能座舱控制系统架构进行设计,并对各个模块进行了详细的阐述。其次,对Q-Learning... 针对智能座舱多模态交互系统在复杂的驾驶场景中出现的适应性、鲁棒性不足的问题,文章采用Q-Learning强化学习算法来实现自适应多模态融合控制。首先,对智能座舱控制系统架构进行设计,并对各个模块进行了详细的阐述。其次,对Q-Learning算法的原理以及参数设置进行分析,并对其权重优化过程进行了论述。接着,在三类典型场景下对所提出的自学习多模态融合控制方法进行验证,并用交互案例详细描述控制系统流程。实验结果表明,与固定权重融合控制方法相比,该方法能够更有效地感知场景变化并调整交互策略。最后,总结文章的研究成果,并指出研究的不足。 展开更多
关键词 智能座舱 多模态融合 控制系统架构 Q-Learning
暂未订购 下载PDF
基于Q-Learning长尾延迟优化的SSD-SMR写缓存策略研究 认领 引用 被引量：1
17
作者 刘健 章步镐 +4 位作者 方匡弛 刘宣锋 孙国道 梁荣华 梁浩然 《计算机工程》 CAS CSCD 北大核心 2026年第3期287-298,共12页
随着全球数据规模的不断增大,如何以低成本的方式有效提升数据的访问性能是存储系统面临的一项重要挑战,使用低延迟、高带宽的固态硬盘(SSD)和低成本、高存储密度的叠瓦式磁盘(SMR)来构建缓存系统,成为一种有效的解决方案。但是,SMR固... 随着全球数据规模的不断增大,如何以低成本的方式有效提升数据的访问性能是存储系统面临的一项重要挑战,使用低延迟、高带宽的固态硬盘(SSD)和低成本、高存储密度的叠瓦式磁盘(SMR)来构建缓存系统,成为一种有效的解决方案。但是,SMR固有的机械运动和多磁道堆叠的特性导致其写性能较差,SSD中的脏数据频繁写回SMR所导致的大量读-合并-写(RMW)操作可能会引起严重的长尾延迟现象。为此,基于SSD-SMR混合存储架构提出一种结合强化学习Q-Learning算法的缓存替换优化策略。通过学习SMR设备的I/O负载状况与延迟之间的经验知识来控制对SMR的写入,当SMR负载较大时,通过控制缓存中脏数据的逐出来减少SMR因写回而产生的大量RMW操作,从而优化系统在不同负载下的尾部延迟开销。将Q-Learning算法与基于数据流行度的缓存算法LRU以及SMR感知的缓存算法SAC进行结合,使用真实企业Trace和YCSB生成的模拟Trace进行测试,实验结果表明,所提方法能够有效提升现有缓存算法的性能,可以降低57.06%的平均延迟和87.49%的尾部延迟。 展开更多
关键词 Q-Learning算法 I/O负载 长尾延迟 缓存替换算法 混合存储
暂未订购 下载PDF
基于遗传算法与Q-learning算法的无人机低能耗协同路径规划 认领 引用
18
作者 曾文岐 陆健强 +3 位作者 兰玉彬 王婷 苏柳 史凯涛 《农业工程学报》 EI CAS CSCD 北大核心 2026年第11期270-280,共11页
针对复杂农业环境下无人机多航点路径规划过程中存在的能耗较高、路径转向频繁及收敛稳定性不足等问题,该研究提出一种融合改进Q学习与遗传算法的低能耗路径规划方法(improved Q-learning genetic algorithm,IQL-GA)。首先,采用墨卡托... 针对复杂农业环境下无人机多航点路径规划过程中存在的能耗较高、路径转向频繁及收敛稳定性不足等问题,该研究提出一种融合改进Q学习与遗传算法的低能耗路径规划方法(improved Q-learning genetic algorithm,IQL-GA)。首先,采用墨卡托投影构建无人机二维作业环境地图,并综合考虑路径长度、转向代价及障碍物规避成本,建立无人机综合能耗模型。其次,用改进型遗传算法进行全局搜索,通过选择、交叉和变异操作生成多模态候选路径集,有效维持解空间多样性并规避局部最优陷阱;将遗传算法得出的优质非支配解映射为Q-table初始值,采用Q-learning算法结合Boltzmann探索策略与能耗惩罚项进行局部精细化调整;再通过2-opt局部搜索消除路径交叉,进一步降低飞行能耗。最后,通过仿真试验与实地飞行测试对算法性能进行验证。消融试验表明,IQL-GA算法在能源利用效率方面优于标准GA和QL算法,路径总能耗分别降低11.6%和19.0%,同时保持低碰撞率与近优路径成本;对比试验表明,与模拟退火算法(simulated annealing,SA)、粒子群优化算法(particle swarm optimization,PSO)及另外两种混合算法相比,IQL-GA算法的平均能耗降低了13.0%。田间试验结果共同验证了该算法的工程实用价值。该研究为资源受限条件下的无人机自主导航提供了解决方案,具有良好的应用前景。 展开更多
关键词 无人机 路径规划 遗传算法 Q-learning 能耗优化
暂未订购 下载PDF
FAIR-DQL:Fairness-Aware Deep Q-Learning for Enhanced Resource Allocation and RIS Optimization in High-Altitude Platform Networks 认领 引用
19
作者 Muhammad Ejaz Muhammad Asim +1 位作者 Mudasir Ahmad Wani Kashish Ara Shakil 《Computers, Materials & Continua》 SCIE EI 2026年第3期758-779,共22页
The integration of High-Altitude Platform Stations(HAPS)with Reconfigurable Intelligent Surfaces(RIS)represents a critical advancement for next-generation wireless networks,offering unprecedented opportunities for ubi... The integration of High-Altitude Platform Stations(HAPS)with Reconfigurable Intelligent Surfaces(RIS)represents a critical advancement for next-generation wireless networks,offering unprecedented opportunities for ubiquitous connectivity.However,existing research reveals significant gaps in dynamic resource allocation,joint optimization,and equitable service provisioning under varying channel conditions,limiting practical deployment of these technologies.This paper addresses these challenges by proposing a novel Fairness-Aware Deep Q-Learning(FAIRDQL)framework for joint resource management and phase configuration in HAPS-RIS systems.Our methodology employs a comprehensive three-tier algorithmic architecture integrating adaptive power control,priority-based user scheduling,and dynamic learning mechanisms.The FAIR-DQL approach utilizes advanced reinforcement learning with experience replay and fairness-aware reward functions to balance competing objectives while adapting to dynamic environments.Key findings demonstrate substantial improvements:9.15 dB SINR gain,12.5 bps/Hz capacity,78%power efficiency,and 0.82 fairness index.The framework achieves rapid 40-episode convergence with consistent delay performance.These contributions establish new benchmarks for fairness-aware resource allocation in aerial communications,enabling practical HAPS-RIS deployments in rural connectivity,emergency communications,and urban networks. 展开更多
关键词 Wireless communication high-altitude platform station reconfigurable intelligent surfaces deep Q-learning
暂未订购 下载PDF
基于改进Q-learning遗传算法求解流水线车间调度问题 认领 引用
20
作者 朱传财 徐坚磊 +2 位作者 鞠立涛 王战 胡燕海 《机床与液压》 北大核心 2026年第7期104-110,共7页
针对置换流水线车间调度问题的NP-hard特性及传统遗传算法参数设置策略固定、收敛效率不足的问题,提出一种基于Q-learning的改进遗传算法。该算法通过强化学习动态调整交叉与变异策略,并结合变邻域下降法增强局部搜索能力。Q-learning... 针对置换流水线车间调度问题的NP-hard特性及传统遗传算法参数设置策略固定、收敛效率不足的问题,提出一种基于Q-learning的改进遗传算法。该算法通过强化学习动态调整交叉与变异策略,并结合变邻域下降法增强局部搜索能力。Q-learning模块以迭代进度、多样性、适应度变化等种群状态为输入,通过状态空间与动作集的映射实现探索、平衡、开发3种策略的自适应切换。对Car类和Rec类测试集数据进行仿真,以最优相对误差、平均相对误差和最差相对误差为衡量指标。结果显示:所提算法在19个案例中找到精确解,其BRE、ARE和WRE指标显著优于对比算法,验证了其求解PFSP的有效性与优越性。该方法可更高效地为流水线车间制定生产调度方案,从而最小化最大完工时间,增强企业在市场中的竞争力。 展开更多
关键词 置换流水线车间调度问题 Q-learning模块 遗传算法 变邻域下降法 动态策略
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 … 250 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈