检索结果-内蒙古大学图书馆

IEEE International Conference on Communications (ICC)

作者： Joseph, Geethu Gursoy, M. Cenk Varshney, Pramod K. Syracuse Univ Dept Elect Engn & Comp Sci Syracuse NY 13244 USA

ISBN: (纸本)9781728171227

We address the problem of sequentially selecting and observing processes from a given set to find the anomalies among them. The decision maker observes one process at a time and obtains a noisy binary indicator of whether or not the corresponding process is anomalous. In this setting, we develop an anomaly detection algorithm that chooses the process to be observed at a given time instant, decides when to stop taking observations, and makes a decision regarding the anomalous processes. The objective of the detection algorithm is to arrive at a decision with an accuracy exceeding a desired value while minimizing the delay in decision making. Our algorithm relies on a Markov decision process defined using the marginal probability of each process being normal or anomalous, conditioned on the observations. We implement the detection algorithm using the deep actor-critic reinforcement learning framework. Unlike prior work on this topic that has exponential complexity in the number of processes, our algorithm has computational and memory requirements that are both polynomial in the number of processes. We demonstrate the efficacy of our algorithm using numerical experiments by comparing it with the state-of-the-art methods.

关键词： Active hypothesis testing anomaly detection deep learning reinforcement learning actor-critic algorithm quickest state estimation sequential decision-making sequential sensing

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning with Iterative Shift for Visual Tracking 15th

Deep Reinforcement Learning with Iterative Shift for Visual ...

引用

15th European Conference on Computer Vision (ECCV)

作者： Ren, Liangliang Yuan, Xin Lu, Jiwen Yang, Ming Zhou, Jie Tsinghua Univ Beijing Peoples R China Horizon Robot Inc Beijing Peoples R China

ISBN: (纸本)9783030012403;9783030012397

Visual tracking is confronted by the dilemma to locate a target both accurately and efficiently, and make decisions online whether and how to adapt the appearance model or even restart tracking. In this paper, we propose a deep reinforcement learning with iterative shift (DRL-IS) method for single object tracking, where an actor-critic network is introduced to predict the iterative shifts of object bounding boxes, and evaluate the shifts to take actions on whether to update object models or re-initialize tracking. Since locating an object is achieved by an iterative shift process, rather than online classification on many sampled locations, the proposed method is robust to cope with large deformations and abrupt motion, and computationally efficient since finding a target takes up to 10 shifts. In offline training, the critic network guides to learn how to make decisions jointly on motion estimation and tracking status in an end-to-end manner. Experimental results on the OTB benchmarks with large deformation improve the tracking precision by 1.7% and runs about 5 times faster than the competing state-of-the-art methods.

关键词： Visual object tracking Reinforcement learning actor-critic algorithm

来源：评论

学校读者我要写书评

暂无评论

Policy Space Noise in Deep Deterministic Policy Gradient 25th

Policy Space Noise in Deep Deterministic Policy Gradient

引用

25th International Conference on Neural Information Processing (ICONIP)

作者： Yan, Yan Liu, Quan Soochow Univ Sch Comp Sci & Technol Suzhou 215006 Jiangsu Peoples R China Collaborat Innovat Ctr Novel Software Technol & I Nanjing 210000 Peoples R China Jilin Univ Minist Educ Key Lab Symbol Computat & Knowledge Engn Changchun 130012 Peoples R China

ISBN: (纸本)9783030041793;9783030041786

Deep deterministic policy gradient (DDPG) algorithm is an attractive reinforcement learning method, which directly optimizes the policy and has good performance in many continuous control tasks. In DDPG, the agent explores the environment by using the Gaussian white noise in the action space. In this paper, to further improve the efficiency of exploration, we inject the factorized Gaussian noise straightly to the policy space and propose a novel dithering perturbation way that can affect subsequent states in the future, resulting in more abundant trajectories. The noise is sampled from a Gaussian noise distribution and learned together with the network weight. In order to guarantee the effectiveness of the perturbation, the same perturbation ratio is used on all layers. Our method does not require augment the environment's reward signal with additional intrinsic motivation term and the agent can learn directly from the environment. The proposed DDPG with exploratory noise in policy space was tested on the continuous control tasks. The experimental results demonstrate that it achieved better performance than the methods with no noise or action space noise.

关键词： Deep reinforcement learning Exploratory noise actor-critic algorithm Deterministic policy gradient

来源：评论

学校读者我要写书评

暂无评论

Learning-Based Task Offloading for Mobile Edge Computing

Learning-Based Task Offloading for Mobile Edge Computing

引用

IEEE International Conference on Communications (ICC)

作者： Garaali, Rim Chaieb, Cirine Ajib, Wessam Afif, Meriem Univ Quebec Montreal Dept Comp Sci Montreal PQ Canada Univ Carthage Natl Inst Appl Sci & Technol Tunis Tunisia

ISBN: (数字)9781538683477

ISBN: (纸本)9781538683477

Mobile edge computing (MEC) is an important technology for latency-sensitive applications. One of the biggest challenges in MEC is efficiently allocating resources under strict QoS requirements and resource constraints. The purpose of this paper is to study the joint problem of computation offloading and resource allocation in such networks. The problem is formulated as a mixed-integer non-convex optimization problem and is proved to be NP-hard. In order to solve it efficiently, we propose a multi-agent deep reinforcement learning solution based on actor-critic method. To reduce system latency, each agent aims to learn interactively the best offloading policy independently of other agents. The simulation results illustrate the performance and advantages of the proposed solution compared to benchmark solutions.

关键词： Mobile edge computing task offloading deep reinforcement learning actor-critic algorithm

来源：评论

学校读者我要写书评

暂无评论

Search Parameter Optimization of Phased Array Radar with Multi-antenna Array Based on Proximal Policy Optimization 36

Search Parameter Optimization of Phased Array Radar with Mul...

引用

36th Chinese Control and Decision Conference (CCDC)

作者： Mo, Xiuci Wang, Teng Hu, Weidong Zhang, Hairuo Li, Xiaoyang Zhou, Deyun Natl Univ Def Technol Natl Key Lab Automat Target Recognit Changsha Peoples R China Northwestern Polytech Univ Sch Elect & Informat Xian Peoples R China

ISBN: (纸本)9798350387780;9798350387797

An optimization algorithm of multi-antenna array radar search parameters based on proximal policy optimization is proposed to solve the problem that the parameters of traditional single-antenna array radar optimization model is hard to solve in complex multi-antenna array scenario. Firstly, considering the constraints of multi-antenna array scenario, combined with the actual search task requirement of airborne radar, an optimization model of multi-antenna array radar search parameters based on the maximum expected discovery distance of the target is established. Secondly, the dual observation space and composite reward function with discount factor are introduced to transform the above optimization problem into a dynamic decision problem of reinforcement learning, in which the solution of model parameters is realized by executable action output by the policy network. Using the actor-critic algorithm structure, combined with methods for solving extreme value of function, the weight of each antenna array and the corresponding sub-airspace search resource allocation coefficient are updated online. Finally, the simulation results show that the proposed algorithm can quickly make accurate autonomous decision based on the airspace-target set covering model and the threat of each target, and the performance of proposed algorithm is significantly better than the traditional algorithm in the multi-antenna array scenario.

关键词： reinforcement learning phased array radar multi-antenna array actor-critic algorithm optimization of search parameters

来源：评论

学校读者我要写书评

暂无评论

Resilient Multi-agent Reinforcement Learning Using Medoid and Soft-medoid Based Aggregation

Resilient Multi-agent Reinforcement Learning Using Medoid an...

引用

IEEE International Conference on Assured Autonomy (ICAA)

作者： Bhowmick, Chandreyee Shabbir, Mudassir Abbas, Waseem Koutsoukos, Xenofon Vanderbilt Univ Inst Software Integrated Syst 221 Kirkland Hall Nashville TN 37235 USA Univ Texas Dallas Dept Syst Engn Richardson TX USA

ISBN: (纸本)9781665485395

A network of reinforcement learning (RL) agents that cooperate with each other by sharing information can improve learning performance of control and coordination tasks when compared to non-cooperative agents. However, networked Multi-agent Reinforcement Learning (MARL) is vulnerable to adversarial agents that can compromise some agents and send malicious information to the network. In this paper, we consider the problem of resilient MARL in the presence of adversarial agents that aim to compromise the learning algorithm. First, the paper presents an attack model which aims to degrade the performance of a target agent by modifying the parameters shared by an attacked agent. In order to improve the resilience, the paper presents aggregation methods using medoid and soft-medoid. Our analysis shows that the medoid-based MARL algorithms converge to an optimal solution given standard assumptions, and improve the overall learning performance and robustness. Simulation results show the effectiveness of the aggregation methods compared with average and median-based aggregation.

关键词： actor-critic algorithm adversarial attacks multi-agent reinforcement learning neural networks resilient aggregation

来源：评论

学校读者我要写书评

暂无评论

An online Q-learning design for stochastic differential LQ game with completely unknown dynamics 41

An online Q-learning design for stochastic differential LQ g...

引用

第41届中国控制会议

作者： Baoqiang Zhang Bingchang Wang School of Control Science and Engineering Shandong University Shandong University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In this paper,we design a reinforcement learning algorithm to solve the adaptive optimal control problem of linear quadratic stochastic non-zero sum differential game with n-players and completely unknown *** is difficult to solve a set of coupled Riccati equations by the traditional method,for the complete system dynamics are *** first use an action dependent value function Q for each actor to replace the state dependent value function *** each player,a critical network is used to estimate the Q function,an actor network is used to estimate the control *** states and the actions of the system constitute the turning ***,a model-free online Q-learning algorithm for solving this kind of problems is *** is proved that the algorithm converges to Nash equilibrium under some conditions.A simulation example with two players is given to verify the effectiveness of the algorithm.

关键词： nonzero-sum stochastic game actor-critic algorithm model-free adaptive control reinforcement learning(RL)

来源：评论

学校读者我要写书评

暂无评论

Estimating reaction barriers with deep reinforcement learning

引用

Data Science 2024年第2期7卷 73-92页

作者： Pal, Adittya Institut for Matematik Og Datalogi Syddansk Universitet Campusvej 55 Odense 5230 Denmark

Stable states in complex systems correspond to local minima on the associated potential energy surface. Transitions between these local minima govern the dynamics of such systems. Precisely determining the transition pathways in complex and high-dimensional systems is challenging because these transitions are rare events, and isolating the relevant species in experiments is difficult. Most of the time, the system remains near a local minimum, with rare, large fluctuations leading to transitions between minima. The probability of such transitions decreases exponentially with the height of the energy barrier, making the system's dynamics highly sensitive to the calculated energy barriers. This work aims to formulate the problem of finding the minimum energy barrier between two stable states in the system's state space as a cost-minimization problem. It is proposed to solve this problem using reinforcement learning algorithms. The exploratory nature of reinforcement learning agents enables efficient sampling and determination of the minimum energy barrier for transitions. © 2024-The authors. Published by IOS Press.

关键词： actor-critic algorithm Deep reinforcement learning minimum energy pathways reaction energy barrier

来源：评论

学校读者我要写书评

暂无评论

A Research on Generative Adversarial Networks Applied to Text Generation 14

A Research on Generative Adversarial Networks Applied to Tex...

引用

14th International Conference on Computer Science and Education (ICCSE)

作者： Zhang, Chao Xiong, Caiquan Wang, Lingyun Hubei Univ Technol Sch Comp Sci Wuhan Peoples R China

ISBN: (纸本)9781728118468

Using deep learning methods to generate text, a sequence-to-sequence model is typically used. This kind of models is very effective in dealing with tasks that have a strong correspondence between input and output, such as machine translation. Generative Adversarial Networks(GAN) is a generation model that has been proposed in recent years, which has achieved good results in generating continuous and divisible data such as images. This paper proposes an improved model based on GAN, specifically using the transformer network structure instead of the original general Convolutional Neural Network or Recurrent Neural Networks as generator, and using the reinforcement learning algorithm actor-critic to improve the model training method. By comparing experiments, and selecting the perplexity, the BLEU score, and the percentages of unique n-gram to evaluate the quality of the generated sentences. The results show that the improved model proposed in this paper perform better than comparative models on above three evaluation indexes. This verifies its effectiveness in text generation.

关键词： Generative adversarial networks Transformer actor-critic algorithm Text generation

来源：评论

学校读者我要写书评

暂无评论

Autonomous UAV with Learned Trajectory Generation and Control 33

Autonomous UAV with Learned Trajectory Generation and Contro...

引用

33rd IEEE International Workshop on Signal Processing Systems (IEEE SiPS)

作者： Li, Yilan Li, Mingyang Sanyal, Amit Wang, Yanzhi Qiu, Qinru Syracuse Univ Dept Elect Engn & Comp Sci Syracuse NY 13244 USA Northeastern Univ Dept Elect & Comp Engn Boston MA 02115 USA

ISBN: (纸本)9781728119274

Unmanned aerial vehicle (UAV) technology is a rapidly growing field with tremendous opportunities for research and applications. To achieve true autonomy for UAVs in the absence of remote control, external navigation aids like global navigation satellite systems and radar systems, a minimum energy trajectory planning that considers obstacle avoidance and stability control will be the key. Although this can be formulated as a constrained optimization problem, due to the complicated non-linear relationships between UAV trajectory and thrust control, it is almost impossible to be solved analytically. While deep reinforcement learning is known for its ability to provide model free optimization for complex system through learning, its state space, actions and reward functions must be designed carefully. This paper presents our vision of different layers of autonomy in a UAV system, and our effort in generating and tracking the trajectory both using deep reinforcement learning (DRL). The experimental results show that compared to conventional approaches, the learned trajectory will need 20% less control thrust and 18% less time to reach the target. Furthermore, using the control policy learning by DRL, the UAV will achieve 58.14% less position error and 21.77% less system power.

关键词： Deep reinforcement learning continuous trajectory tracking actor-critic algorithm unmanned aerial vehicles

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：