dodox/metastable-baselines
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

.

Browse Source
This commit is contained in:
Dominik Moritz Roth 2023-01-28 21:47:19 +01:00
parent b86498fa9a
commit 71670782b6
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
metastable_baselines/ppo/policies.py
View File

@ -88,7 +88,7 @@ class ActorCriticPolicy(BasePolicy):
activation_fn: Type[nn.Module] = nn.Tanh, activation_fn: Type[nn.Module] = nn.Tanh,
ortho_init: bool = True, ortho_init: bool = True,
use_sde: bool = False, use_sde: bool = False,
log_std_init: float = 0.0, std_init: float = 1.0,
full_std: bool = True, full_std: bool = True,
sde_net_arch: Optional[List[int]] = None, sde_net_arch: Optional[List[int]] = None,
use_expln: bool = False, use_expln: bool = False,
@ -135,7 +135,7 @@ class ActorCriticPolicy(BasePolicy):
self.features_dim = self.features_extractor.features_dim self.features_dim = self.features_extractor.features_dim
self.normalize_images = normalize_images self.normalize_images = normalize_images
self.log_std_init = log_std_init self.log_std_init = math.log(std_init)
# Keyword arguments for gSDE distribution # Keyword arguments for gSDE distribution
if dist_kwargs == None: if dist_kwargs == None:
dist_kwargs = {} dist_kwargs = {}

4
metastable_baselines/sac/policies.py
View File

@ -265,7 +265,7 @@ class SACPolicy(BasePolicy):
net_arch: Optional[Union[List[int], Dict[str, List[int]]]] = None, net_arch: Optional[Union[List[int], Dict[str, List[int]]]] = None,
activation_fn: Type[nn.Module] = nn.ReLU, activation_fn: Type[nn.Module] = nn.ReLU,
use_sde: bool = False, use_sde: bool = False,
log_std_init: float = -3, std_init: float = 0.05,
sde_net_arch: Optional[List[int]] = None, sde_net_arch: Optional[List[int]] = None,
use_expln: bool = False, use_expln: bool = False,
clip_mean: float = 2.0, clip_mean: float = 2.0,
@ -314,7 +314,7 @@ class SACPolicy(BasePolicy):
sde_kwargs = { sde_kwargs = {
"use_sde": use_sde, "use_sde": use_sde,
"log_std_init": log_std_init, "log_std_init": math.log(std_init),
"use_expln": use_expln, "use_expln": use_expln,
"clip_mean": clip_mean, "clip_mean": clip_mean,
} }