wassname/ray
1
0
Fork 0
mirror of https://github.com/wassname/ray.git synced 2026-06-27 20:22:39 +08:00
Code Issues Packages Projects Releases Wiki Activity

[rllib] Entropy calculation for diag gaussian missing 0.5 term (#2968)

Browse Source 
See: https://en.wikipedia.org/wiki/Multivariate_normal_distribution#Entropy
This commit is contained in:
Eric Liang
2018-09-29 22:57:47 -07:00
committed by Richard Liaw
parent b3f0dcf20b
commit cb56f39070
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/ray/rllib/models/action_dist.py
+1 -1
View File
@@ -125,7 +125,7 @@ class DiagGaussian(ActionDistribution):
def entropy(self):
return tf.reduce_sum(
self.log_std + .5 * np.log(2.0 * np.pi * np.e),
.5 * self.log_std + .5 * np.log(2.0 * np.pi * np.e),
reduction_indices=[1])
def sample(self):