saymrwulf/stable-baselines3
1
0
Fork 0
mirror of https://github.com/saymrwulf/stable-baselines3.git synced 2026-07-30 20:18:15 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add comment about warmup phase

Browse source
This commit is contained in:
Antonin Raffin 2020-01-07 17:36:26 +01:00
parent 8831eff163
commit 299ca007b5
1 changed files with 2 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
torchy_baselines/common/base_class.py
View file

@ -526,6 +526,8 @@ class BaseRLModel(object):
self.actor.reset_noise()
# 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:
# Warmup phase
unscaled_action = np.array([self.action_space.sample()])