Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Terlipressin for septic shock patients: a meta-analysis of randomized controlled study.

Journal of intensive care·2019
Same author

One-step synthesis of hexylresorcinol calix[4]arene-capped ZnO-Ag nanocomposites for enhanced degradation of organic pollutants.

Journal of colloid and interface science·2019
Same author

Facile fabrication of visible light photoelectrochemical immunosensor for SCCA detection based on BiOBr/Bi<sub>2</sub>S<sub>3</sub> heterostructures via self-sacrificial synthesis method.

Talanta·2019
Same author

Rice seed priming with sodium selenate: Effects on germination, seedling growth, and biochemical attributes.

Scientific reports·2019
Same author

Coupling S-adenosylmethionine-dependent methylation to growth: Design and uses.

PLoS biology·2019
Same author

A prostate-specific antigen electrochemical immunosensor based on Pd NPs functionalized electroactive Co-MOF signal amplification strategy.

Biosensors & bioelectronics·2019
Same journal

Hidden Data Recovery and Forecasting via Next-Generation Reservoir Computing With Multiscale Delay Selection.

IEEE transactions on neural networks and learning systems·2026
Same journal

CAFF-CIL: Causality-Aware Freedom Forgetting Approach for Class-Incremental Learning.

IEEE transactions on neural networks and learning systems·2026
Same journal

Harmonic Autoencoding Framework for Multiple Tasks in Magnetic Particle Imaging Reconstruction.

IEEE transactions on neural networks and learning systems·2026
Same journal

A Survey on Human-Centric Voice-Face Multimodal Learning.

IEEE transactions on neural networks and learning systems·2026
Same journal

Vision-Assisted Foundation Model for Solving Multitask Vehicle Routing Problems.

IEEE transactions on neural networks and learning systems·2026
Same journal

FP3O: Enabling Proximal Policy Optimization in Multiagent Cooperation With Parameter-Sharing Versatility.

IEEE transactions on neural networks and learning systems·2026
查看所有相关文章

相关实验视频

Updated: Jul 11, 2025

Real-Time Proxy-Control of Re-Parameterized Peripheral Signals using a Close-Loop Interface
11:54

Real-Time Proxy-Control of Re-Parameterized Peripheral Signals using a Close-Loop Interface

Published on: May 8, 2021

4.4K

安全的适应性政策转移强化学习,用于分布式多代理控制.

Bin Du, Wei Xie, Yang Li

    IEEE transactions on neural networks and learning systems
    |November 2, 2023
    PubMed
    概括
    此摘要是机器生成的。

    本研究介绍了一种安全的自适应性政策转移强化学习 (RL) 方法. 它使后续代理从先驱代理学习,改善合作控制和安全.

    更多相关视频

    WheelCon: A Wheel Control-Based Gaming Platform for Studying Human Sensorimotor Control
    08:18

    WheelCon: A Wheel Control-Based Gaming Platform for Studying Human Sensorimotor Control

    Published on: August 15, 2020

    5.0K
    A Networked Desktop Virtual Reality Setup for Decision Science and Navigation Experiments with Multiple Participants
    06:28

    A Networked Desktop Virtual Reality Setup for Decision Science and Navigation Experiments with Multiple Participants

    Published on: August 26, 2018

    6.0K

    相关实验视频

    Last Updated: Jul 11, 2025

    Real-Time Proxy-Control of Re-Parameterized Peripheral Signals using a Close-Loop Interface
    11:54

    Real-Time Proxy-Control of Re-Parameterized Peripheral Signals using a Close-Loop Interface

    Published on: May 8, 2021

    4.4K
    WheelCon: A Wheel Control-Based Gaming Platform for Studying Human Sensorimotor Control
    08:18

    WheelCon: A Wheel Control-Based Gaming Platform for Studying Human Sensorimotor Control

    Published on: August 15, 2020

    5.0K
    A Networked Desktop Virtual Reality Setup for Decision Science and Navigation Experiments with Multiple Participants
    06:28

    A Networked Desktop Virtual Reality Setup for Decision Science and Navigation Experiments with Multiple Participants

    Published on: August 26, 2018

    6.0K

    科学领域:

    • 人工智能的人工智能
    • 机器学习 机器学习
    • 机器人技术 机器人技术 机器人技术

    背景情况:

    • 多代理强化学习 (RL) 培训是具有挑战性的,因为代理干扰和安全限制.
    • 现有的方法在合作的多代理系统中难以有效地转移知识和适应性学习.

    研究的目的:

    • 为多代理合作控制提出安全的适应性政策转移RL方法.
    • 通过知识转移,提高多代理系统的学习效率和安全性.

    主要方法:

    • 引入了一种先驱和追随者非政策政策转移学习 (PFOPT) 方法.
    • 使政策代表和样本经验从先驱转移到追随者代理.
    • 利用瓦瑟斯坦距离,在先前的经验和探索之间适应调整学习权重.

    主要成果:

    • 训练有素的分布式代理成功完成了协作任务,最大限度地提高了奖励,同时最大限度地减少了约束违规行为.
    • 与基线方法相比,在学习速度和成功率方面表现令人满意.
    • 通过PFOPT方法,有效地转移知识,并根据政策分配差异调整学习.

    结论:

    • 提出的安全适应性政策转移RL方法显著改善了多代理合作控制.
    • 对于复杂的多代理培训场景,PFOPT提供了一种高效和安全的解决方案.
    • 这种方法为分散式系统中的知识共享和适应性学习提供了强大的框架.