检索结果-南通市图书馆

Robust cooperative multi-agent reinforcement learning via multi-view message certification

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第4期67卷 131-145页

作者： Lei YUAN Tao JIANG Lihe LI Feng CHEN Zongzhang ZHANG Yang YU National Key Laboratory for Novel Software Technology Nanjing University Polixir technologies

Many multi-agent scenarios require message sharing among agents to promote coordination,hastening the robustness of multi-agent communication when policies are deployed in a message perturbation environment. Major relevant studies tackle this issue under specific assumptions, like a limited number of message channels would sustain perturbations, limiting the efficiency in complex scenarios. In this paper,we take a further step in addressing this issue by learning a robust cooperative multi-agent reinforcement learning via multi-view message certification, dubbed CroMAC. Agents trained under CroMAC can obtain guaranteed lower bounds on state-action values to identify and choose the optimal action under a worst-case deviation when the received messages are perturbed. Concretely, we first model multi-agent communication as a multi-view problem, where every message stands for a view of the state. Then we extract a certificated joint message representation by a multi-view variational autoencoder(MVAE) that uses a product-of-experts inference network. For the optimization phase, we do perturbations in the latent space of the state for a certificate guarantee. Then the learned joint message representation is used to approximate the certificated state representation during training. Extensive experiments in several cooperative multi-agent benchmarks validate the effectiveness of the proposed CroMAC.

关键词： multi-agent reinforcement learning robust communication adversarial training multi-view learning message certification

Shape embedding and retrieval in multi-ﬂow deformation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computational Visual Media 2024年第3期10卷 439-451页

作者： Baiqiang Leng Jingwei Huang Guanlin Shen Bin Wang School of Software Tsinghua UniversityBeijingChina Huawei technologies ShenzhenChina

We propose a unified 3D ﬂow frameworkfor joint learning of shape embedding and deformationfor different categories. Our goal is to recovershapes from imperfect point clouds by fitting thebest shape template in a shape repository afterdeformation. Accordingly, we learn a shape embeddingfor template retrieval and a ﬂow-based network forrobust deformation. We note that the deformationﬂow can be quite different for different shapecategories. Therefore, we introduce a novel multi-hubmodule to learn multiple modes of deformation toincorporate such variation, providing a network whichcan handle a wide range of objects from differentcategories. The shape embedding is designed to retrievethe best-fit template as the nearest neighbor in a latentspace. We replace the standard fully connected layerwith a tiny structure in the embedding that significantlyreduces network complexity and further improvesdeformation quality. Experiments show the superiorityof our method to existing state-of-the-art methods viaqualitative and quantitative comparisons. Finally, ourmethod provides efficient and flexible deformation thatcan further be used for novel shape design.

关键词： deformation shape retrieval embedding reconstruction

Reinforcement Learning-Empowered Graph Convolutional Network Framework for Data Integrity Attack Detection in Cyber-Physical Systems

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CSEE Journal of Power and Energy Systems 2024年第2期10卷 797-806页

作者： Edeh Vincent Mehdi Korki Mehdi Seyedmahmoudian Alex Stojcevski Saad Mekhilef School of Science Computingand Engineering TechnologiesSwinburne University of TechnologyMelbourneAustralia

The massive integration of communication and information technology with the large-scale power grid has enhanced the efficiency, safety, and economical operation of cyber-physical systems. However, the open and diversified communication environment of the smart grid is exposed to cyber-attacks. Data integrity attacks that can bypass conventional security techniques have been considered critical threats to the operation of the grid. Current detection techniques cannot learn the dynamic and heterogeneous characteristics of the smart grid and are unable to deal with non-euclidean data types. To address the issue, we propose a novel Deep-Q-Network scheme empowered with a graph convolutional network (GCN) framework to detect data integrity attacks in cyber-physical systems. The simulation results show that the proposed framework is scalable and achieves higher detection accuracy, unlike other benchmark techniques.

关键词： Deep reinforcement learning graph convolutional network heterogeneous smart grid network

Research progress,doping strategies and dielectric-ferroelectric anomalies of rare earth-based Bi0.5Na0.5TiO3 perovskites

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Rare Earths 2024年第11期42卷 2003-2017页

作者： Subramani Supriya Research Rhombus technologies (RR Tech-Non-profit and Non-commercial)

Rare earth-based functional perovskites have received significant attention due to increasing energy crisis problems and environmental *** non-toxic,lead-free materials have been investigated;bismuth sodium titanate(Bi0.5Na0.5TiO3) has gotten significant attention because of its unique morphological,structural,and electrical ***,the emergence of bismuth sodium titanate with a high remnant polarization has revived the application of inorganic materials in electronic *** type of ferroelectrics is known to display new functionalities coupled with ferroic *** recent years,research in the field of inorganic-based ferroelectrics,mainly Bi0.5Na0.5TiO3（BNT）,has been thriving toward enhanced electronic device *** rare earth elements in BNT compounds has achieved significant electrical *** article summarizes prominent theories associated with ferroelectric-dielectric mechanisms and provides the most recent progress in rare earth-based BNT *** is placed on design of principles toward tailoring the crystal structure via doping effect and oxygen vacancies,as well as domain ***,the critical investigation is accompanied by future perspectives,including integrating rare earth BNT perovskites for high-performance ferroelectric devices.

关键词： BNT Crystal structure Dielectric Doping Ferroelectric Rare earth elements

Congener-derived template to construct lithiophilic organic-inorganic layer/interphase for high volumetric capacity dendrite-free Li metal batteries

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Chemical Letters 2024年第3期35卷 453-460页

作者： Kang Yang Long Li Yuanbin Xiao Qiaoli Zhang Chenpeng Xi Borong Li Yan Yu Chengkai Yang Key Laboratory of Advanced Materials technologies International(HongKong Macao and Taiwan)Joint Laboratory on Advanced Materials TechnologiesCollege of Materials Science and EngineeringFuzhou UniversityFuzhou 350108China

The development of lithium-metal batteries(LMBs)is seriously restricted by the out-of-control dendrites growth and infinite volume ***,a pervasive organic-inorganic layer construction strategy is reported for the composite lithium metal anode with congener-derived organic-inorganic solid electrolyte interphase(SEI).In this strategy,the organic-inorganic Ag@polydopamine(Ag@PDA)layer is coated on the arbitrary substrates by a simple two-step *** thin and stable congener-derived SEI is insitu formed with fewer inorganic components and more organic components during charging/*** polydopamine with sufficient adhesion groups and lithiophilic Ag layer realize near-zero nucleation overpotential during lithium *** low interface resistance and stable lithium deposition are ***,the practical areal and volumetric capacities of the composite anode with three-dimensional copper(3DCu)as the substrate are 10 mAh/cm^(2)and 1538 mAh/cm^3(*** mass of anode).The symmetrical cell shows very low polarization voltage(10 mV)and more than 2500 h cycles life at 1 mA/cm^(2)(1 mAh/cm^(2)).The LiNi_(0.8)Co_(0.1)Mn_(0.1)O_(2)(NCM811)-based full cells show improved capacity retention(82%)after 100 cycles at 0.5 *** modified lithiophilic anode with congener-derived interphase provides a promising strategy to realize the next-generation dendrite-free LMBs.

关键词： Lithium metal anode Congener-derived Lithiophilicity Volumetric capacity Organic-inorganic interphase

Managing the surge:A comprehensive review of the entire disposal framework for retired lithium-ion batteries from electric vehicles

在线全文

学校读者我要写书评

暂无评论

Journal of Energy Chemistry 2024年第5期92卷 648-680页

作者： Ruohan Guo Feng Wang M.Akbar Rhamdhani Yiming Xu Weixiang Shen Department of Engineering technologies School of ScienceComputing and Engineering TechnologiesSwinburne University of TechnologyMelbourne VIC 3122Australia Department of Chemistry and Biotechnology School of ScienceComputing and Engineering TechnologiesSwinburne University of TechnologyMelbourne VIC 3122Australia Department Mechanical and Product Design Engineering School of EngineeringSwinburne University of TechnologyMelbourne VIC 3122Australia

Anticipating the imminent surge of retired lithium-ion batteries(R-LIBs)from electric vehicles,the need for safe,cost-effective and environmentally friendly disposal technologies has *** paper seeks to offer a comprehensive overview of the entire disposal framework for R-LIBs,encompassing a broad spectrum of activities,including screening,repurposing and ***,we delve deeply into a thorough examination of current screening technologies,shifting the focus from a mere enumeration of screening methods to the exploration of the strategies for enhancing screening ***,we outline battery repurposing with associated key factors,summarizing stationary applications and sizing methods for R-LIBs in their second life.A particular light is shed on available reconditioning solutions,demonstrating their great potential in facilitating battery safety and lifetime in repurposing scenarios and identifying their techno-economic *** the realm of battery recycling,we present an extensive survey of pre-treatment options and subsequent material recovery ***,we introduce several global leading recyclers to illustrate their industrial processes and technical ***,relevant challenges and evolving trends are investigated in pursuit of a sustainable end-of-life management and disposal *** hope that this study can serve as a valuable resource for researchers,industry professionals and policymakers in this field,ultimately facilitating the adoption of proper disposal practices.

关键词： Lithium-ion battery Battery reproposing and recycling Miaieiials recovery technologies Techno-economic issues End-of-life management Disposal framework

Learning in games:a systematic review

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第7期67卷 133-159页

作者： Rong-Jun QIN Yang YU National Key Laboratory for Novel Software Technology Nanjing University Polixir technologies

Game theory studies the mathematical models for self-interested individuals. Nash equilibrium is arguably the most central solution in game theory. While finding the Nash equilibrium in general is known as polynomial parity arguments on directed graphs(PPAD)-complete, learning in games provides an alternative to approximate Nash equilibrium, which iteratively updates the player's strategy through interactions with other players. Rules and models have been developed for learning in games, such as fictitious play and no-regret learning. Particularly, with recent advances in online learning and deep reinforcement learning,techniques from these fields greatly boost the breakthroughs in learning in games from theory to *** a result, we have witnessed many superhuman game AI systems. The techniques used in these systems evolve from conventional search and learning to purely reinforcement learning(RL)-style learning methods,gradually getting rid of the domain knowledge. In this article, we systematically review the above techniques,discuss the trend of basic learning rules towards a unified framework, and recap applications in large ***, we discuss some future directions and make the prospect of future game AI systems. We hope this article will give some insights into designing novel approaches.

关键词： non-cooperative games learning in games no-regret learning reinforcement learning superhuman AI

Communication-robust multi-agent learning by adaptable auxiliary multi-agent adversary generation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2024年第6期18卷 186331-186331页

作者： YUAN Lei CHEN Feng ZHANG Zongzhang YU Yang National Key Laboratory for Novel Software Technology Nanjing University Polixir technologies

Communication can promote coordination in cooperative Multi-Agent Reinforcement Learning (MARL). Nowadays, existing works mainly focus on improving the communication efficiency of agents, neglecting that real-world communication is much more challenging as there may exist noise or potential attackers. Thus the robustness of the communication-based policies becomes an emergent and severe issue that needs more exploration. In this paper, we posit that the ego system trained with auxiliary adversaries may handle this limitation and propose an adaptable method of Multi-Agent Auxiliary Adversaries Generation for robust Communication, dubbed MA3C, to obtain a robust communication-based policy. In specific, we introduce a novel message-attacking approach that models the learning of the auxiliary attacker as a cooperative problem under a shared goal to minimize the coordination ability of the ego system, with which every information channel may suffer from distinct message attacks. Furthermore, as naive adversarial training may impede the generalization ability of the ego system, we design an attacker population generation approach based on evolutionary learning. Finally, the ego system is paired with an attacker population and then alternatively trained against the continuously evolving attackers to improve its robustness, meaning that both the ego system and the attackers are adaptable. Extensive experiments on multiple benchmarks indicate that our proposed MA3C provides comparable or better robustness and generalization ability than other baselines.

关键词： multi-agent communication adversarial training robustness validation reinforcement learning

Antisense therapy:a potential breakthrough in the treatment of neurodegenerative diseases

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Neural Regeneration Research 2024年第5期19卷 1027-1035页

作者： Roberta Romano Cecilia Bucci Department of Biological and Environmental Sciences and technologies(DiSTeBA) University of SalentoLecceItaly

Neurodegenerative diseases are a group of disorders characterized by the progressive degeneration of neurons in the central or peripheral nervous ***,there is no cure for neurodegenerative diseases and this means a heavy burden for patients and the health system ***,it is necessary to find new therapeutic approaches,and antisense therapies offer this possibility,having the great advantage of not modifying cellular genome and potentially being *** preclinical and clinical studies aim to test the safety and effectiveness of antisense therapies in the treatment of neurodegenerative *** objective of this review is to summarize the recent advances in the development of these new technologies to treat the most common neurodegenerative diseases,with a focus on those antisense therapies that have already received the approval of the *** and Drug Administration.

关键词： Alzheimer’s disease amyotrophic lateral sclerosis antisense oligonucleotide Huntington’s disease neurodegenerative disorders Parkinson’s disease siRNA