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

你这个A2C是不是跟别人有点不一样 #1

Open
caozhenxiang-kouji opened this issue Jan 24, 2018 · 1 comment
Open

你这个A2C是不是跟别人有点不一样 #1

caozhenxiang-kouji opened this issue Jan 24, 2018 · 1 comment

Comments

@caozhenxiang-kouji
Copy link

别人很多A2C是一步一更新,你这个是每一轮过后总的更新一次

@JIElite
Copy link

JIElite commented Mar 4, 2018

It seems to use n-steps learning in this implementation, which n is 30(SAMPLE_NUMS = 30)?

I have another question about this implementation:
[Q] As far as I know, A2C is a synchronous version of A3C. In order to deal with correlation issue, we use multiple workers in A3C so as A2C. However, in this version, It doesn't support multiple workers which may cause learning biased.

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

No branches or pull requests

2 participants