google-deepmind / google-deepmind/scalable_agent
Replay buffer?
Open
- Dominant language
- Python
- Stars
- 1k
- Forks
- 160
- PR merge metrics
- No merged PRs in 30d
Description
I cannot find a replay buffer in this implementation. Is the data from the actors discarded after being trained for one iteration？
Contributor guide
Assessment
This issue has not been assessed yet.