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

Jump to bottom

how to get the score of an expert policy and some other details #16

Closed

TianhongDai opened this issue Jul 26, 2021 · 1 comment

TianhongDai commented Jul 26, 2021

Hi,

Thanks for sharing this interesting work. However, I have few questions in the paper:

Could I know how to get the score of an expert policy that you used to normalize the score in Tables? If possible, could you share these information, please?
When you report the results in the paper (e.g., Table 4), which score do you use - the score in the last epoch or the best score during training?

Looking forward to your reply!

Best Wishes

Owner

kzl commented Aug 1, 2021

For Atari, see Table 11 in Appendix B. For D4RL, see the benchmarking paper, also located here.
We use the last epoch, although we found this was not significant (in contrast, TD learning algorithms tend to be very sensitive to this).

kzl closed this as completed

linprophet mentioned this issue

The results on Mujoco reported in paper might be heavily influenced by env version #42

Open

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