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

Question on PPO entropy coefficient #35

Open
mpeschina opened this issue Feb 16, 2023 · 0 comments
Open

Question on PPO entropy coefficient #35

mpeschina opened this issue Feb 16, 2023 · 0 comments

Comments

@mpeschina
Copy link

Hi,
I have a question about the entropy coefficient c2 of PPO and its standard value in SIMPLE.
In the original paper, the "standard" value is c2=0.01 but in SIMPLE its set to c2=0.1
"parser.add_argument("--entcoeff", "-ent", type = float, default = 0.1, help="The entropy coefficient in PPO")"

Is there a reason to put the standard value so high in SIMPLE? I am currently trying to tune that value and I am just curious.

Kind regards,
Markus

(Paper: https://arxiv.org/pdf/1707.06347.pdf)

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

1 participant