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.

Sign up for GitHub

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

Sampling of VPG should be over D*T #361

Open

HunderlineK wants to merge 1 commit into openai:master from HunderlineK:patch-1

HunderlineK commented Mar 11, 2022 •

edited

Loading

I'm not 100% sure if this change is correct, but in the code we have:

    def compute_loss(obs, act, weights):
        logp = get_policy(obs).log_prob(act)
        return -(logp * weights).mean()

Where we average the loss over the total number of the observations.

I have also tried averaging just over D and the result doesn't improve properly.


Sampling of VPG should be over D*T

d2d1496

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment