Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

/chapter5/chapter5_questions&keywords #55

Open
qiwang067 opened this issue May 24, 2021 · 9 comments
Open

/chapter5/chapter5_questions&keywords #55

qiwang067 opened this issue May 24, 2021 · 9 comments

Comments

@qiwang067
Copy link
Contributor

https://datawhalechina.github.io/easy-rl/#/chapter5/chapter5_questions&keywords

Description

@Strawberry47
Copy link

总结的超级好,谢谢博主!

@yyysjz1997
Copy link
Contributor

总结的超级好,谢谢博主!
谢谢~

@Strawberry47
Copy link

代码部分我有一个小小的疑问:为什么actor的输出(即输入state,产生action的概率)要命名为dist呀?是distance的简写吗?

@FulChou
Copy link

FulChou commented Nov 11, 2021 via email

@Strawberry47
Copy link

@CSU-FulChou
我理解成是动作的分布,所以是distribution的意思

发自我的iPhone

------------------ Original ------------------
From: Strawberry47 @.>
Date: Thu,Nov 11,2021 4:00 PM
To: datawhalechina/easy-rl @.
>
Cc: Subscribed @.***>
Subject: Re: [datawhalechina/easy-rl] /chapter5/chapter5_questions&keywords (#55)

代码部分我有一个小小的疑问:为什么actor的输出(即输入state,产生action的概率)要命名为dist呀?是distance的简写吗?


You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub, or unsubscribe.
Triage notifications on the go with GitHub Mobile for iOS or Android.

啊啊,是哈,我疏忽了,Thanks♪(・ω・)ノ

@Strawberry47
Copy link

啊,代码部分我还有一个critic_loss计算问题:是Q_value(old)-critic_value(new),这样算的吗?不知道理解的对不对~

@JimmyYoungggg
Copy link

请问博主PPO算法里的θk多久更新一次?如果是每次迭代都更新的话,那采样效率岂不是依然不高?

@littlebrotherdog
Copy link

@JimmyYoungggg
请问博主PPO算法里的θk多久更新一次?如果是每次迭代都更新的话,那采样效率岂不是依然不高?

update policy every n steps

    if self.sample_count % self.update_freq != 0:
        return

看代码,频率可以自己设置的。

@littlebrotherdog
Copy link

@Strawberry47
啊,代码部分我还有一个critic_loss计算问题:是Q_value(old)-critic_value(new),这样算的吗?不知道理解的对不对~

critic_loss = (returns - values).pow(2).mean()
这里做了一个MSE,critic这个网络是用来估计V的。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

6 participants