Haitham Bou Ammar RL team leader @Huawei R&D UK & UCL H. Assistant Prof.

发布于 2022-03-02 22:47:19

Iterated Law of Expectation Consice Proof (6 simple steps)

课程学习 #离线强化学习 #多智能体强化学习 #ml-agents

浏览 (1361) 点赞 (3) 收藏

评论(1)

Willing Star 2023-07-11 19:41:42 回复

I think the R.H.S. is better written as E[E[Y|X=x,Z]|X=x], because Z is also a random variable.

Haitham Bou Ammar

RL team leader @Huawei R&D UK & UCL H. Assistant Prof.

关注了
4
关注者
17
积分
8
注册排名
539