Examples for using Imitation Learning / Offline RL Algorithms

[batu]

• I have marked all applicable categories:
  • exception-raising bug
  • RL algorithm bug
  • system worker bug
  • system utils bug
  • code design/refactor
  • documentation request
  • new feature request
• I have visited the readme and doc
• I have searched through the issue tracker and pr tracker
• [N/A] I have mentioned version numbers, operating system and environment, where applicable:

  import ding, torch, sys
  print(ding.__version__, torch.__version__, sys.version, sys.platform)

Hello, first of all thank you for this great looking open source project!

I am interested in comparing Implicit BC to other RL algorithms. I have of course seen the workflow to use the RL algorithms, but I couldn't find documentation on how to load data for BC/Offline RL algorithms.

Would documentation on that be possible?

Thank you

[PaParaZz1]

Thanks for you interests for our repo.

For the data pipeline of BC/offline training, including generating data, loading data, offline training and other steps, we will add a best practice documentation in this week, you can follow this issue and add your comments.

[PaParaZz1]

@batu You can refer to this PR and give some review comments.