open_spiel
open_spiel copied to clipboard
Incorrect docstring in policy_gradient.py
https://github.com/deepmind/open_spiel/blob/f4ae28033cc1f92ca4cc9f8bc87477ba9c8c4237/open_spiel/python/algorithms/policy_gradient.py
Hi, The docstring states the critic learning rate is 0.001, but it really defaults to 0.01. It has the same issue in PPO, etc., I guess it's related to some copy-pasting or something similar :)
Thanks
Thanks, good find! Can you submit a PR to fix the instances you found?
Sure, I will work on it as soon as I can.
@lanctot I have made the appropriate changes and made a PR for that, Please Merge it if this is correct, otherwise let me know if any modifications need to be made.
Perfect thanks. Should be merged on Monday.