sweetice/Deep-reinforcement-learning-with-pytorch

About SAC's version bug (gym 0.17.3)

CoderAT13 opened this issue · 1 comments

CoderAT13 commented

In SAC.py

  1. NormalizedActions(gym.ActionWrapper)
    _action -> action
    _reverse_action -> reverse_action

  2. Before env.render(), must use env.reset()

rl-max commented

I had a problem with this(I didn't notice syntax's change) . Thank you so much!!