search

sweetice / Deep-reinforcement-learning-with-pytorch

PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....
MIT License
3.88k stars 844 forks source link

About SAC's version bug (gym 0.17.3) #21

Open CoderAT13 opened 3 years ago

CoderAT13 commented 3 years ago

In SAC.py

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

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

rl-max commented 3 years ago

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