Add N-Step Returns to TD Buffers
Open
enhancement
- Dominant language
- Python
- Stars
- 61
- Forks
- 2
- PR merge metrics
- No merged PRs in 30d
Description
Check the enhancements here: https://github.com/hill-a/stable-baselines/issues/821
Additionally, check: https://seohong.me/blog/q-learning-is-not-yet-scalable/
Contributor guide
Assessment
This issue has not been assessed yet.