[归纳]强化学习导论 - 第七章:n-step自举(Bootstrapping)-CSDN博客

网站介绍:文章浏览阅读3.3k次,点赞5次,收藏17次。文章目录本章内容概要n-step TD Predictionn-step Sarsan-step Off-policy Learning*Per-decision Methods with Control VariatesOff-policy Learning Without Importance Sampling: The n-step Tree Backup Algorithm*A Unify..._n-step