dodox/metastable-baselines2
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Better default HPs for TRPL

Browse Source
This commit is contained in:
Dominik Moritz Roth 2024-01-23 09:20:34 +01:00
parent 5b9f8b028c
commit e3f4c511bf
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
metastable_baselines2/trpl/trpl.py
View File

@ -87,7 +87,7 @@ class TRPL(BetterOnPolicyAlgorithm):
n_epochs: int = 10, n_epochs: int = 10,
gamma: float = 0.99, gamma: float = 0.99,
gae_lambda: float = 0.95, gae_lambda: float = 0.95,
clip_range: Union[float, Schedule] = 0.2, clip_range: Union[float, Schedule, None] = None,
clip_range_vf: Union[None, float, Schedule] = None, clip_range_vf: Union[None, float, Schedule] = None,
normalize_advantage: bool = True, normalize_advantage: bool = True,
ent_coef: float = 0.0, ent_coef: float = 0.0,
@ -169,7 +169,11 @@ class TRPL(BetterOnPolicyAlgorithm):
) )
self.batch_size = batch_size self.batch_size = batch_size
self.n_epochs = n_epochs self.n_epochs = n_epochs
if clip_range == False:
clip_range = None
self.clip_range = clip_range self.clip_range = clip_range
if clip_range_vf == False:
clip_range_vf = None
self.clip_range_vf = clip_range_vf self.clip_range_vf = clip_range_vf
self.normalize_advantage = normalize_advantage self.normalize_advantage = normalize_advantage
self.projection = castProjection(projection) self.projection = castProjection(projection)