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

Success returns the same value for both reward and done #57

Closed
raghada opened this issue Apr 7, 2020 · 2 comments
Closed

Success returns the same value for both reward and done #57

raghada opened this issue Apr 7, 2020 · 2 comments

Comments

@raghada
Copy link

raghada commented Apr 7, 2020

def success(self):

Am I missing something?

@bycn
Copy link

bycn commented Apr 12, 2020

sparse reward, so rew = 1 = done = True, rew = 0 = done = False

@stepjam
Copy link
Owner

stepjam commented Apr 12, 2020

Hi both. What @bycn is not quite right; what he said is true on the environment level (calling env.step). However, that particular success function was originally going to return both success value and if any constraints were breached, but I decided not to include it, hence why it returns the same value for both. I will refactor this out in future.

I wouldn't worry too much about it as its a backend function and you shouldn't need to use it.

@stepjam stepjam closed this as completed Apr 12, 2020
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

3 participants