A New Accelerated Off-Policy Stochastic Preconditioned TD(0) Algorithm
IEEE transactions on pattern analysis and machine intelligence(2025)
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