mirror of
https://github.com/saymrwulf/stable-baselines3.git
synced 2026-11-18 09:54:10 +00:00
Add comment about warmup phase
This commit is contained in:
parent
8831eff163
commit
299ca007b5
1 changed files with 2 additions and 0 deletions
|
|
@ -526,6 +526,8 @@ class BaseRLModel(object):
|
||||||
self.actor.reset_noise()
|
self.actor.reset_noise()
|
||||||
|
|
||||||
# Select action randomly or according to policy
|
# Select action randomly or according to policy
|
||||||
|
# TODO: use action from policy when using SDE during the warmup phase?
|
||||||
|
# if num_timesteps < learning_starts and not self.use_sde:
|
||||||
if num_timesteps < learning_starts:
|
if num_timesteps < learning_starts:
|
||||||
# Warmup phase
|
# Warmup phase
|
||||||
unscaled_action = np.array([self.action_space.sample()])
|
unscaled_action = np.array([self.action_space.sample()])
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue