Results 21 to 30 of about 2,703 (160)
Study on Intelligent Recommendation Method of Dueling Network Reinforcement Learning Based on Regret Exploration [PDF]
, 2022 In recent years,the application of deep reinforcement learning in recommendation system has attracted much attention.Based on the existing research,this paper proposes a new recommendation model RP-Dueling,which is based on the deep reinforcement ...
HONG Zhi-li, LAI Jun, CAO Lei, CHEN Xi-liang, XU Zhi-xiong
core +1 more source
智能科学与技术学报, 2022 随着基础理论和硬件计算能力的飞速发展，深度学习技术在众多领域取得了令人瞩目的成绩。作为描述客观物理世界的重要工具，长期以来微分方程是各领域研究人员关心的重点。近年来，深度学习和微分方程的结合逐渐成了研究的热点。由于深度学习能够从大量数据中高效地提取特征，微分方程能够反应客观的物理规律，因此二者的结合可以有效地提升深度学习的泛化性，同时增强深度学习的可解释性。首先，介绍了深度学习求解微分方程的基本问题。其次，介绍了两类深度学习求解微分方程的方法：数据驱动和物理知情方法。然后 ...
卢经纬, 程相, 王飞跃
doaj
Deep reinforcement learning based task allocation mechanism for intelligent inspection in energy Internet [PDF]
, 2021 In order to reduce the cost and improve efficiency of power line inspection, UAV (unmanned aerial vehicle), which use mobile edge computing technology to access and process service data, are used to inspect power lines in the energy internet.However, due
Chao YANG +5 more
core +1 more source
Resource allocation strategy based on deep reinforcement learning in 6G dense network [PDF]
, 2023 In order to realize no overlapping interference between cells, 6G dense network (DN) adopting resource allocation is the important technology of enhancing network performance.However, limited resources and dense distribution of nodes make it difficult to
Cheng YANG +6 more
core +1 more source
Guangtongxin yanjiu, 2021 在大力发展智能电网的背景下，支撑电网运转的电力光通信网规模日趋庞大，其承载的业务更加多样化。然而电力光通信网的业务路由规划主要以最短路径算法为主，导致电力光通信网存在业务重要度分布不均衡，从而导致网络局部风险过高的问题。针对上述现状，文章采用深度强化学习技术，以网络业务风险均衡为目标，提出了基于强化学习的电力光通信网风险均衡路由算法。该算法考虑业务重要度分布情况、链路容量和链路光信噪比，实现了电力光通信网风险均衡化。文章选取某省电力通信子网验证方案的有效性，研究结果表明 ...
张庚 +5 more
doaj
Intelligent transmit power control algorithm for the multi-user interference of wireless network [PDF]
, 2022 To deal with the inter-user interference problem in wireless networks, an intelligent transmit power control scheme was proposed to manage the inter-user interference and guarantee multiple users' quality of service.Firstly, considering the complex ...
Haijun YE +3 more
core +1 more source
智能科学与技术学报, 2022 群体行为往往能产生远超个体行为的价值和复杂度。为了在个体智能的基础上更有效地衍生出群体智能，需要基于群体熵来科学地衡量群体智能水平，并以群体熵为引导目标，推动群体智能的增强和演进。针对这个重要的科学问题，以无人小车群体为研究对象，提出基于参数共享和群体策略熵的多智能体soft Q learning算法，通过共享智能体的观测信息，并结合最大熵强化学习方法，实现探索型任务中群体策略的持续学习更新。同时，通过将群体熵定义为度量工具，刻画群体学习中熵变化模式，实现对群智汇聚过程的定量分析。
冯埔 +4 more
doaj +1 more source
智能科学与技术学报, 2020 深度强化学习主要被用来处理感知-决策问题，已经成为人工智能领域重要的研究分支。概述了基于值函数和策略梯度的两类深度强化学习算法，详细阐述了深度Q网络、深度策略梯度及相关改进算法的原理，并综述了深度强化学习在视频游戏、导航、多智能体协作以及推荐系统等领域的应用研究进展。最后，对深度强化学习的算法和应用进行展望，针对一些未来的研究方向和研究热点给出了建议。
刘朝阳, 穆朝絮, 孙长银
doaj
Deep Reinforcement Learning-driven Cross-Community Energy Interaction Optimal Scheduling
, 2023 In order to coordinate energy interactions among various communities and energy conversions among multi-energy subsystems within the multi-community integrated energy system under uncertain conditions, and achieve overall optimization and scheduling of ...
Bu, Fanjin +5 more
core
Joint optimization of edge computing and caching in NDN [PDF]
, 2022 Named data networking (NDN) is architecturally easier to integrate with edge computing as its routing is based on content names and its nodes have caching capabilities.Firstly, an integrated framework was proposed for implementing dynamic coordination of
Min CHENG, Yu ZHANG
core +1 more source