Question on benchmark hyperparameters

[RolandStolz]

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

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

First of all, thank you for the very detailed benchmark descriptions. That is truly amazing! However, I am having trouble finding the specific hyperparameters used for the benchmarks.

Are the used hyperparameters just the ones provided in the default arguments (e.g. lines 25-75 in examples/mujoco/mujoco_ppo.py)? If so, that would mean that you used the same hyperparameters for all mujoco environments, which I hardly believe is the case. I feel like I'm missing something here.

Any help is greatly appreciated!

[Trinkle23897]

I believe it's the default hyperparameter. You can checkout the commit mentioned in the benchmark page and see what's actually ran at that time.