gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2025-12-17 11:10:20 +01:00
Code Issues Projects Releases Wiki Activity

Distiller's AMC induced changes (#359)

Browse Source 
* override episode rewards with the last transition reward

* EWMA normalization filter

* allowing control over when the pre_network filter runs
This commit is contained in:
Gal Leibovich
2019-08-05 10:24:58 +03:00
committed by GitHub
parent 7df67dafa3
commit c1d1fae342
10 changed files with 137 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
rl_coach/exploration_policies/truncated_normal.py
View File

@@ -88,9 +88,6 @@ class TruncatedNormal(ContinuousActionExplorationPolicy):
else:
action_values_std = current_noise
# scale the noise to the action space range
action_values_std = current_noise * (self.action_space.high - self.action_space.low)
# extract the mean values
if isinstance(action_values, list):
# the action values are expected to be a list with the action mean and optionally the action stdev