diff --git a/PPO.py b/PPO.py index 9a171a2..f79f02d 100644 --- a/PPO.py +++ b/PPO.py @@ -52,6 +52,7 @@ def __init__(self, state_dim, action_dim, has_continuous_action_space, action_st nn.Linear(64, 64), nn.Tanh(), nn.Linear(64, action_dim), + nn.Tanh() ) else: self.actor = nn.Sequential(