谷歌浏览器插件
订阅小程序
在清言上使用

A New Accelerated Off-Policy Stochastic Preconditioned TD(0) Algorithm

Weidong Liu, Jiahua Ma,Xiaojun Mao, Kejie Tang

IEEE transactions on pattern analysis and machine intelligence(2025)

引用 0|浏览1
关键词
Off-policy,policy evaluation,linear approximation,temporal-difference learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要