Labels

Add new algorithm or improve old one

Something isn't working

Update config

Questions about training data

Discussion of a typical issue

Documentation

Add or update dockerfile

This issue or pull request already exists

Efficiency optimization (time, memory and so on)

New feature or request

Questions about RL environment

Good for newcomers

Extra attention is needed

Issue that must be fixed in short order

Issue that should be fixed within a few weeks

Important issue, but not time-critical

Issue moderate in impact or severity

Parallel and distributed training related

refactor module or component

Algorithm and efficiency reproducibility

Serial training related

Test(unittest, performance, efficiency, compatibility)

Fix typo

This will not be worked on