• 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, torch, numpy, sys
  print(tianshou.__version__, torch.__version__, numpy.__version__, sys.version, sys.platform)
  0.4.5 1.7.1.post2 1.19.5 3.8.10 | packaged by conda-forge | (default, May 11 2021, 07:01:05) 
  [GCC 9.3.0] linux

Hey guys,
I found a bug where networks and optimizers for SAC critics are different when saved compared to unsaved objects.
The issue doesn't occur with actor, actor optimizer and alpha.

Gist with code to replicate the problem:
https://gist.github.com/jacekplocharczyk/a85964c5ad227b88af00dfb1a4dfd769