多智能体深度强化学习的若干关键科学问题
孙长银， 穆朝絮 - 自动化学报, 2020 - aas.net.cn
… insights into various research directions of multi-agent reinforcement learning, and related
ideas for … A survey of learning in multiagent environments: dealing with non-stationarity. arXiv: …
ideas for … A survey of learning in multiagent environments: dealing with non-stationarity. arXiv: …
多Agent 深度强化学习综述
梁星星， 冯旸赫， 马扬， 程光权， 黄金才， 王琦， 周玉珍… - 自动化学报, 2020 - aas.net.cn
… To enable DRL better accommodate the multi-agent environment and overcome challenges,
we … A survey of learning in multiagent environments: Dealing with non-stationarity. arXiv …
we … A survey of learning in multiagent environments: Dealing with non-stationarity. arXiv …
基于对手动作预测的智能博弈对抗算法.
韩润海， 陈浩， 刘权， 黄健 - Journal of Computer …, 2023 - search.ebscohost.com
… scenario, the multi-agent reinforcement learning algorithm has the problem of“non
stationarity”. The … F,RAHMAN A,et al. dealing with non-stationarity in multi-agent deep reinforcement …
stationarity”. The … F,RAHMAN A,et al. dealing with non-stationarity in multi-agent deep reinforcement …
[HTML][HTML] 基于LSTM Dueling Double DQN 的车联网分布式资源管理算法
陈志鹏 - Computer Science and Application, 2023 - hanspub.org
… in V2X communication environment is studied. Firstly, a multi-agent temporal information …
本文的创新之处在于用独特的状态表示来处理多智能体学习系统中的非平稳性(Non-Stationarity…
本文的创新之处在于用独特的状态表示来处理多智能体学习系统中的非平稳性(Non-Stationarity…
基于学习机制的多智能体强化学习综述
王若男， 董琦 - 工程科学学报, 2024 - cje.ustb.edu.cn
… learning trajectory of multiagent systems and simultaneously … of multiagent reinforcement
learning, focusing on the manifold … Dealing with nonstationary environments using context …
learning, focusing on the manifold … Dealing with nonstationary environments using context …
面向多智能体博弈对抗的对手建模框架
罗俊仁， 张万鹏， 袁唯淋， 胡振震， 陈少飞… - 系统仿真学报, 2022 - china-simulation.com
… 面向多智能体决策的模型主要 有多智能体MDPs(multi-agent MDPs, MMDPs)及 分布式
MDPs(decentralized MDPs, Dec-MDPs)[9]. 其中在MMDPs 模型中,主要采用集中式的策略, 不区分单个…
MDPs(decentralized MDPs, Dec-MDPs)[9]. 其中在MMDPs 模型中,主要采用集中式的策略, 不区分单个…
多智能体博弈, 学习与控制
王龙， 黄锋 - 自动化学报, 2023 - aas.net.cn
… Subsequently, following different research topics, we survey the latest interdisciplinary
research … A survey of learning in multiagent environments: Dealing with non-stationarity. arXiv: …
research … A survey of learning in multiagent environments: Dealing with non-stationarity. arXiv: …
未知环境下无人机集群智能协同探索路径规划
王伟伦， 尤明， 孙磊， 张秀云， 宗群 - 工程科学学报, 2024 - cje.ustb.edu.cn
… a wide range of variability in environmental conditions, a single unmanned aerial …
learning-based approach for the collaborative exploration of multiple UAVs in unknown …
learning-based approach for the collaborative exploration of multiple UAVs in unknown …
智能博弈对抗中的对手建模方法及其应用综述.
魏婷婷， 袁唯淋， 罗俊仁 - Journal of Computer Engineering …, 2022 - search.ebscohost.com
… A survey of learning in multiagent environments: dealing with non-stationarity[EB/OL].(2019-03-11)[202106-01].https://arxiv.org/abs/1707.09183v1.
[17] 罗俊仁,张万鹏,袁唯淋,等,面向多…
[17] 罗俊仁,张万鹏,袁唯淋,等,面向多…
[PDF][PDF] 應用空間統計於桃園地區土地利用變遷因素分析
張文菘， 陳嘉惠， 張國楨 - 地理研究, 2017 - researchgate.net
… Innovation in spatial statistics methods has helped handle … This study used a spatial
autocorrelation index to detect the … (drift),形成空間不穩定(non-stationarity).由於傳統線性迴歸視影響…
autocorrelation index to detect the … (drift),形成空間不穩定(non-stationarity).由於傳統線性迴歸視影響…