检索结果-内蒙古大学图书馆

Enabling Surrogate-Assisted Evolutionary Reinforcement Learning via Policy Embedding 1

17th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2022

作者： Tang, Lan Li, Xiaxi Zhang, Jinyuan Li, Guiying Yang, Peng Tang, Ke Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Faculty of Engineering Shenzhen MSU-BIT University Shenzhen518172 China Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen518055 China Department of Statistics and Data Science Southern University of Science and Technology Shenzhen518055 China

ISBN: (数字)9789819915491

ISBN: (纸本)9789819915484

Evolutionary Reinforcement Learning (ERL) that applying Evolutionary Algorithms (EAs) to optimize the weight parameters of Deep Neural Network (DNN) based policies has been widely regarded as an alternative to traditional reinforcement learning methods. However, the evaluation of the iteratively generated population usually requires a large amount of computational time and can be prohibitively expensive, which may potentially restrict the applicability of ERL. Surrogate is often used to reduce the computational burden of evaluation in EAs. Unfortunately, in ERL, each individual of policy usually represents millions of weights parameters of DNN. This high-dimensional representation of policy has introduced a great challenge to the application of surrogates into ERL to speed up training. This paper proposes a PE-SAERL Framework to at the first time enable surrogate-assisted evolutionary reinforcement learning via policy embedding (PE). Empirical results on 5 Atari games show that the proposed method can perform more efficiently than the four state-of-the-art algorithms. The training process is accelerated up to 7x on tested games, comparing to its counterpart without the surrogate and PE. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Comparative sensitivity analysis of single and multiple modifications in multi-criteria decision analysis 28th

Comparative sensitivity analysis of single and multiple modi...

引用

28th International Conference on Knowledge Based and intelligent information and Engineering systems, KES 2024

作者： Wieckowski, Jakub Bialon, Pawel Salabun, Wojciech Research Team on Intelligent Decision Support Systems Department of Artificial Intelligence and Applied Mathematics Faculty of Computer Science and Information Technology West Pomeranian University of Technology Szczecin ul. Zolnierska 49 Szczecin71-210 Poland National Institute of Telecommunications ul. Szachowa 1 Warsaw04-894 Poland

In the area of decision-making, where complexities often exceed experts' analytical capabilities, this study addresses a critical gap by introducing a novel methodology for sensitivity analysis within the Multi-Criteria Decision Analysis (MCDA) problems. Current analytical frameworks struggle to comprehensively consider potential modifications to values within decision matrices, making it challenging to understand their impact in detail. To address this challenge, decision-makers need enhanced tools, and MCDA methods combined with systematic changes in selected elements of the decision matrix stand out as a promising approach. However, existing studies primarily focus on different criteria-weight scenarios, leaving an unexplored gap in the simultaneous modification of multiple values within the decision matrix. This paper integrates sensitivity analysis within the MCDA methods, extending its role in the comprehensive assessment of decision problems. Sensitivity analysis becomes crucial in offering decision-makers a broader perspective, aiding them in navigating the complexities of decision-making in dynamic environments. Recognizing the unexplored potential in sensitivity analysis, the study proposed a novel approach of simultaneous modification of multiple values in a decision matrix, offering an extension of conventional one-at-a-time modifications. As a Proof of Concept (PoC) research work, the study investigated whether the determined approach provides divergent preference scores compared to the traditional single-modification method across ten different MCDA techniques. The results showed that modifying multiple values simultaneously produced different preference scores of alternatives than in the case of a conventional single change, showing that additional insight knowledge could be extracted from this type of sensitivity analysis. © 2024 The Authors.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Modeling Long-Term Intentions and Narratives in Autonomous Agents

Journal of Artificial Intelligence and Consciousness

引用

Journal of Artificial Intelligence and Consciousness 2021年第2期8卷 229-265页

作者： Kronsted, Christian Neemeh, Zachariah A. Kugele, Sean Franklin, Stan Department of Philosophy and Institute for Intelligent Systems University of Memphis 3720 Alumni Ave Memphis 3815 TN United States Computer Science Department and Institute for Intelligent Systems University of Memphis 3720 Alumni Ave Memphis 3815 TN United States

Across various fields it is argued that the self in part consists of an autobiographical self-narrative and that the self-narrative has an impact on agential behavior. Similarly, within action theory, it is claimed that the intentional structure of coherent long-term action is divided into a hierarchy of distal, proximal, and motor intentions. However, the concrete mechanisms for how narratives and distal intentions are generated and impact action is rarely fleshed out concretely. We here demonstrate how narratives and distal intentions can be generated within cognitive agents and how they can impact agential behavior over long time scales. We integrate narratives and distal intentions into the LIDA model, and demonstrate how they can guide agential action in a manner that is consistent with the Global Workspace Theory of consciousness. This paper serves both as an addition to the LIDA cognitive architecture and an elucidation of how narratives and distal intention emerge and play their role in cognition and action © 2021 World Scientific Publishing Company.

关键词： action theory agency distal intentions global workspace theory intentions LIDA narrative

来源：评论

学校读者我要写书评

暂无评论

Democratizing AI: Open-source Scalable LLM Training on GPU-based Supercomputers

arXiv

引用

arXiv 2025年

作者： Singh, Siddharth Singhania, Prajwal Ranjan, Aditya Kirchenbauer, John Geiping, Jonas Wen, Yuxin Jain, Neel Hans, Abhimanyu Shu, Manli Tomar, Aditya Goldstein, Tom Bhatele, Abhinav Department of Computer Science University of Maryland College Park United States ELLIS Institute Tübingen Max Planck Institute for Intelligent Systems Tübingen Germany Department of Electrical Engineering and Computer Sciences University of California Berkeley United States

Training and fine-tuning large language models (LLMs) with hundreds of billions to trillions of parameters requires tens of thousands of GPUs, and a highly scalable software stack. In this work, we present a novel four-dimensional hybrid parallel algorithm implemented in a highly scalable, portable, open-source framework called AxoNN. We describe several performance optimizations in AxoNN to improve matrix multiply kernel performance, overlap non-blocking collectives with computation, and performance modeling to choose performance optimal configurations. These have resulted in unprecedented scaling and peak flop/s (bf16) for training of GPT-style transformer models on Perlmutter (620.1 Petaflop/s), Frontier (1.381 Exaflop/s) and Alps (1.423 Exaflop/s). While the abilities of LLMs improve with the number of trainable parameters, so do privacy and copyright risks caused by memorization of training data, which can cause disclosure of sensitive or private information at inference time. We highlight this side effect of scale through experiments that explore "catastrophic memorization," where models are sufficiently large to memorize training data in a single pass, and present an approach to prevent it. As part of this study, we demonstrate fine-tuning of a 405-billion parameter LLM using AxoNN on Frontier. Copyright © 2025, The Authors. All rights reserved.

关键词： Supercomputers

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study on the Efficiency of the Modified COMET in Decision-Making 28th

A Comparative Study on the Efficiency of the Modified COMET ...

引用

28th International Conference on Knowledge Based and intelligent information and Engineering systems, KES 2024

作者： Paradowski, Bartosz Olender, Pawel Salabun, Wojciech Research Team on Intelligent Decision Support Systems Department of Artificial Intelligence and Applied Mathematics Faculty of Computer Science and Information Technology West Pomeranian University of Technology Szczecin ul. Zolnierska 49 Szczecin71-210 Poland National Institute of Telecommunications ul. Szachowa 1 Warsaw04-894 Poland

Decision-making is a high-risk area and, simultaneously, a process that cannot be ignored. Risks often arise under challenging situations where ranking the options under consideration is a complex problem. For such purposes, multi-criteria decision-making methods are resorted to, which, despite continuous improvement, still have some weaknesses, often due to their characteristics. One such method that has seen many modifications in the literature is the Characteristic Objects METhod (COMET). It allows a simplified comparison of alternatives considered in a given problem, compared to the Analytic Hierarchy Process (AHP), but has a relatively high computational complexity. In this study, we present a modification of the COMET method that simplifies the procedure for assigning preference values to characteristic objects. Furthermore, a comparison with the classical approach is given regarding the obtained preference values, rankings, and criteria weights, which occur implicitly in this method. The study showed that the proposed modification has grounds for broader use and offers similar results to classical COMET while reducing the number of required operations to obtain preference values. © 2024 The Authors.

关键词： Comets

来源：评论

学校读者我要写书评

暂无评论

NavG: Risk-Aware Navigation in Crowded Environments Based on Reinforcement Learning with Guidance Points

arXiv

引用

arXiv 2025年

作者： Zhang, Qianyi Luo, Wentao Liu, Boyi Zhang, Ziyang Wang, Yaoyuan Liu, Jingtai Institute of Robotics and Automatic Information System Nankai University Tianjin Key Laboratory of Intelligent Robotics Tianjin China Advanced Computing and Storage Lab Huawei 2012 Lab China Department of Electronic and Computer Engineering The Kong Kong University of Science and Technology Hong Kong

Motion planning in navigation systems is highly susceptible to upstream perceptual errors, particularly in human detection and tracking. To mitigate this issue, the concept of guidance points—a novel directional cue within a reinforcement learning-based framework—is introduced. A structured method for identifying guidance points is developed, consisting of obstacle boundary extraction, potential guidance point detection, and redundancy elimination. To integrate guidance points into the navigation pipeline, a perception-to-planning mapping strategy is proposed, unifying guidance points with other perceptual inputs and enabling the RL agent to effectively leverage the complementary relationships among raw laser data, human detection and tracking, and guidance points. Qualitative and quantitative simulations demonstrate that the proposed approach achieves the highest success rate and near-optimal travel times, greatly improving both safety and efficiency. Furthermore, real-world experiments in dynamic corridors and lobbies validate the robot’s ability to confidently navigate around obstacles and robustly avoid pedestrians. © 2025, CC BY.

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

Modelling and Control of a Trailer Sprayer for Precision Spraying

Modelling and Control of a Trailer Sprayer for Precision Spr...

引用

IEEE International Conference on Autonomous Robot systems and Competitions (ICARSC)

作者： André Baltazar Filipe N. Santos Antόnio Paulo Moreira Salviano Pinto Soares M. J. C. S. Reis José Boaventura Cunha CRIIS-Centre for Robotics in Industry and Intelligent Systems INESC TEC—Institute for Systems and Computer Engineering Technology and Science Porto Portugal ECT—School of Science and Technology UTAD—University of Trás-os-Montes and Alto Douro Vila Real Portugal FEUP—Faculty of Engineering University of Porto Porto Portugal Institute of Electronics and Informatics Engineering of Aveiro (IEETA) Portugal Intelligent Systems Associate Laboratory (LASI) Portugal

ISBN: (数字)9798350352344

ISBN: (纸本)9798350352351

Precision spraying in agriculture is crucial for optimizing the application of pesticides while minimizing environmental impact. Despite significant advancements in control models for spraying systems, predictive control algorithms were not used. This paper addresses this gap by proposing a real-time control framework that integrates predictive control strategies to ensure consistent pressure output in a trailer sprayer. Based on information from various sensors, the framework anticipates and adapts to dynamic environmental conditions, enhancing accuracy and sustainability in spraying practices. A methodology is developed to define a proportional valve model. Based on this valve model, the predictive control model optimizes valve movements to minimize errors between predicted and reference pressures, thereby improving spraying efficiency. This study demonstrates the viability of predictive control in improving precision spraying systems applicable to autonomous robots, encouraging future advances in agricultural spraying technologies.

关键词： Adaptation models Spraying Predictive models Valves Real-time systems Agriculture Sensors

来源：评论

学校读者我要写书评

暂无评论

An Isomerism Learning Model to Solve Time-Varying Problems Through intelligent Collaboration

引用

IEEE/CAA Journal of Automatica Sinica 2023年第8期10卷 1772-1774页

作者： Zhihao Hao Guancheng Wang Bob Zhang Leyuan Fang Haisheng Li the Department of Computer and Information Science University of MacaoMacao 999078China the School of Data Science the Chinese University of Hong KongShenzhen 518172 Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen 518000 China Industrial Control Systems Cyber Emergency Response Team Beijing 100040China IEEE the College of Electrical and Information Engineering Hunan UniversityChangsha 410082 the Peng Cheng Laboratory Shenzhen 518000China the Beijing Key Laboratory of Big Data Technology for Food Safety Beijing Technology and Business UniversityBeijing 100048 the School of Computer Science and Engineering Beijing Technology and Business UniversityBeijing 100048China

Dear Editor,This letter deals with a solution for time-varying problems using an intelligent computational(IC)algorithm driven by a novel decentralized machine learning approach called isomerism *** order to meet the challenges of the model’s privacy and security brought by traditional centralized learning models,a private permissioned blockchain is utilized to decentralize the model in order to achieve an effective coordination,thereby ensuring the credibility of the overall model without exposing the specific parameters and solution process.

关键词： ism thereby letter

来源：评论

学校读者我要写书评

暂无评论

Stable Normative Explanations 35

Stable Normative Explanations

引用

35th International Conference on Legal Knowledge and Information systems, JURIX 2022

作者： Governatori, Guido Olivieri, Francesco Rotolo, Antonino Cristani, Matteo Centre for Computational Law Singapore Management University Singapore Institute for Integrated and Intelligent Systems Griffith University Australia Alma Ai University of Bologna Italy Department of Computer Science University of Verona Italy

ISBN: (纸本)9781643683645

Modelling the concept of explanation is a central matter in AI systems, as it provides methods for developing eXplainable AI (XAI). When explanation applies to normative reasoning, XAI aims at promoting normative trust in the decisions of AI systems: in fact, such a trust depends on understanding whether systems predictions correspond to legally compliant scenarios. This paper extends to normative reasoning a work by Governatori et al. (2022) on the notion of stable explanations in a non-monotonic setting: when an explanation is stable, it can be used to infer the same normative conclusion independently of other facts that are found afterwards. © 2022 The authors and IOS Press.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Human Fall Detection Using Transfer Learning-Based 3D CNN 1st

Human Fall Detection Using Transfer Learning-Based 3D CNN

引用

1st International Conference on Computational Technologies and Electronics, ICCTE 2023

作者： Alam, Ekram Sufian, Abu Dutta, Paramartha Leo, Marco Department of Computer Science Gour Mahavidyalaya Old Malda India Department of Computer Science University of Gour Banga English Bazar India Department of Computer and System Sciences Visva-Bharati University Santiniketan India National Research Council of Italy Institute of Applied Sciences and Intelligent Systems Lecce Italy

ISBN: (纸本)9783031819346

Unintentional or accidental falls are one of the significant health issues in senior persons. The population of senior persons is increasing steadily. So, there is a need for an automated fall detection monitoring system. This paper introduces a vision-based fall detection system using a pre-trained 3D CNN. Unlike 2D CNN, 3D CNN extracts not only spatial but also temporal features. Proposed model leverages the original learned weights of a 3D CNN model pre-trained on the Sports1M dataset to extract the spatio-temporal features. Only the SVM classifier was trained, which saves the time required to train the 3D CNN. Stratified shuffle five split cross-validation has been used to split the dataset into training and testing data. Extracted features from the proposed 3D CNN model were fed to an SVM classifier to classify the activity as fall or ADL. Two datasets, GMDCSA and CAUCAFall, were utilized to conduct the experiment. The source code for this work can be accessed via the following link: https://***/ekramalam/HFD_3DCNN. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Fall detection

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：