wassname/pytorch-soft-actor-critic
1
0
Fork 0
mirror of https://github.com/wassname/pytorch-soft-actor-critic.git synced 2026-06-27 16:46:28 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update sac.py

Browse Source
This commit is contained in:
Pranjal Tandon
2020-02-03 13:48:45 +05:30
committed by GitHub
parent 73064f31ea
commit 42d2ff08cb
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
sac.py
+2 -2
View File
@@ -27,7 +27,7 @@ class SAC(object):
if self.policy_type == "Gaussian":
# Target Entropy = −dim(A) (e.g. , -6 for HalfCheetah-v2) as given in the paper
if self.automatic_entropy_tuning == True:
if self.automatic_entropy_tuning is True:
self.target_entropy = -torch.prod(torch.Tensor(action_space.shape).to(self.device)).item()
self.log_alpha = torch.zeros(1, requires_grad=True, device=self.device)
self.alpha_optim = Adam([self.log_alpha], lr=args.lr)
@@ -43,7 +43,7 @@ class SAC(object):
def select_action(self, state, eval=False):
state = torch.FloatTensor(state).to(self.device).unsqueeze(0)
if eval == False:
if eval is False:
action, _, _ = self.policy.sample(state)
else:
_, _, action = self.policy.sample(state)