• 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)

During training, I found that the value of loss is really large, is this normal? I also found that my reward gradually decreased from fluctuations, and finally stabilized at a relatively low value. I guess maybe solving the problem of loss divergence then can solve the problem of reward.
this photo is a screenshot during training