-
Notifications
You must be signed in to change notification settings - Fork 8.6k
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
[Bug Report] Vector env return value #3253
Comments
Without more of your code it is difficult to tell what is happening also this is for v0.18 which is several years old so we wouldn't be updated any code unless this is still an issue now |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Describe the bug
Hi, I used the vector env api in gym to train Atari-PongNoFrameSkip-v4. After the agent interacts with the environment for a period of time, I discovered a strange phenomenon. The cumulative reward was 21.0, but the corresponding done status was still False.
An intuitive example is described below:
In this case, the env reached the max reward cannot be set done. And the cumulative reward would increased. Is this situation normal?
System Info
gym==0.18
The text was updated successfully, but these errors were encountered: