• I have marked all applicable categories:
  • exception-raising bug
  • RL algorithm bug
  • documentation request (i.e. "X is missing from the documentation.")
  • new feature request
• I have visited the source website
• I have searched through the issue tracker for duplicates
• I have mentioned version numbers, operating system and environment, where applicable:

  import tianshou, gym, torch, numpy, sys
  print(tianshou.__version__, gym.__version__, torch.__version__, numpy.__version__, sys.version, sys.platform)

I see that PG and algorithms which inherit from it support LR schedulers. Can we add support for LR schedulers to more algorithms? I'm primarily interested in DDPG and SAC.

As a more ambitious refactor, can we add support for LR schedulers to all algorithms by allowing a tuple of (optim, LR_scheduler) to be used instead of an optim when we want to use a scheduler?