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.

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

feature(wrh): add adaptive batch size for transition #256

Open
wants to merge 4 commits into
base: dev-unizero-multitask-v2
Choose a base branch
from
Open

feature(wrh): add adaptive batch size for transition #256

wants to merge 4 commits into from
+62 −17

Conversation

ruiheng123
Copy link
Contributor

@ruiheng123 ruiheng123 commented Jul 31, 2024 •
edited
Loading

  1. Each env has different steps per episode. We improved the sampling batch size distribution according to the collected steps in the buffer. Env with more collected steps can obtain larger batch size for training.
  2. Meanwhile, we use softmax with temperature T param to keep the difference between different batch sizes from being too large.

@puyuan1996 puyuan1996 added the enhancement New feature or request label Aug 5, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@ruiheng123 @puyuan1996