PARALLELISATION

作品数:1被引量:0H指数:0
导出分析报告
相关期刊:《IET Cyber-Systems and Robotics》更多>>
相关基金:国家自然科学基金更多>>
-

检索结果分析

结果分析中...
条 记 录,以下是1-1
视图:
排序:
A new noise network and gradient parallelisation‐based asynchronous advantage actor‐critic algorithm
《IET Cyber-Systems and Robotics》2022年第3期175-188,共14页Zhengshun Fei Yanping Wang Jinglong Wang Kangling Liu Bingqiang Huang Ping Tan 
Natural Science Foundation of Zhejiang Province,Grant/Award Number:LQ15F030006;Key Research and Development Program of Zhejiang Province,Grant/Award Number:2018C01085。
Asynchronous advantage actor‐critic(A3C)algorithm is a commonly used policy opti-mization algorithm in reinforcement learning,in which asynchronous is parallel inter-active sampling and training,and advantage is a sa...
关键词:ASYNCHRONOUS ADVANTAGE actorcritic (A3C) generalised ADVANTAGE estimation (GAE) PARALLELISATION reinforcement learning 
检索报告 对象比较 聚类工具 使用帮助 返回顶部