这是indexloc提供的服务,不要输入任何密码
Skip to content

Replay buffer allows stack_num = 1 #165

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

Merged
merged 2 commits into from
Jul 25, 2020
Merged

Conversation

duburcqa
Copy link
Collaborator

I think it is more convenient to consider "no stacking" = 1 instead of 0, as it is the case now. It is useful in my case because it enables to increase number of observation steps provided to the model without having to do an exception for "no stack" case.

@duburcqa duburcqa changed the base branch from master to dev July 25, 2020 10:18
@Trinkle23897 Trinkle23897 merged commit 30368c2 into thu-ml:dev Jul 25, 2020
@youkaichao
Copy link
Collaborator

Nice little pr to resolve the legacy inconsistency 👍 Maybe this should be mentioned in release notes.

@duburcqa duburcqa deleted the replay_stack branch July 25, 2020 12:20
BFAnas pushed a commit to BFAnas/tianshou that referenced this pull request May 5, 2024
* stack_num starts at 1 (for no stacking) instead of 0.

* Use getter/stepper for stack_num.

Co-authored-by: Alexis Duburcq <alexis.duburcq@wandercraft.eu>
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

Successfully merging this pull request may close these issues.

3 participants