League Training for SlimeVolleyball Env

[PaParaZz1]

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

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

Overview

Add league training pipeline in slime_volleyball environment, and make better performance than self-play results (#23) Related Discussion: #61

TODO

• [ ] league pipeline
• [ ] mutate from pre-trained model (vs bot)
• [ ] policy behavior analysis

[PaParaZz1]

we will restart this demo in February 28th, and we expect to finish it in a week.

[zxzzz0]

@PaParaZz1 Could we have some updates on this? It's been more than 8 weeks.

[zxzzz0]

we will restart this demo in February 28th, and we expect to finish it in a week.

@PaParaZz1 it's been 6 months, do we complete the tasks below?

• [ ] league pipeline
• [ ] mutate from pre-trained model (vs bot)
• [ ] policy behavior analysis