Fix sde_sample_freq for SAC (#32)

* Fix `sde_sample_freq` for SAC

* [ci skip] Add Acknowledgments

README.md

@@ -227,5 +227,11 @@ Stable-Baselines3 is currently maintained by [Ashley Hill](https://github.com/hi
 To any interested in making the baselines better, there is still some documentation that needs to be done.
 If you want to contribute, please read [**CONTRIBUTING.md**](./CONTRIBUTING.md) guide first.
 
+## Acknowledgments
+
+The initial work to develop Stable Baselines3 was partially funded by the project *Reduced Complexity Models* from the *Helmholtz-Gemeinschaft Deutscher Forschungszentren*.
+
+The original version, Stable Baselines, was created in the [robotics lab U2IS](http://u2is.ensta-paristech.fr/index.php?lang=en) ([INRIA Flowers](https://flowers.inria.fr/) team) at [ENSTA ParisTech](http://www.ensta-paristech.fr/en).
+
 
 Logo credits: [L.M. Tenkes](https://www.instagram.com/lucillehue/)

docs/misc/changelog.rst

@@ -3,7 +3,7 @@
 Changelog
 ==========
 
-Pre-Release 0.6.0a9 (WIP)
+Pre-Release 0.6.0a10 (WIP)
 ------------------------------
 
 Breaking Changes:
@@ -24,6 +24,7 @@ Bug Fixes:
 - Fixed a bug that prevented model trained on cpu to be loaded on gpu
 - Fixed version number that had a new line included
 - Fixed weird seg fault in docker image due to FakeImageEnv by reducing screen size
+- Fixed ``sde_sample_freq`` that was not taken into account for SAC
 
 Deprecations:
 ^^^^^^^^^^^^^

stable_baselines3/common/base_class.py

@@ -798,7 +798,7 @@ class OffPolicyRLModel(BaseRLModel):
 
             while not done:
 
-                if self.use_sde and self.sde_sample_freq > 0 and n_steps % self.sde_sample_freq == 0:
+                if self.use_sde and self.sde_sample_freq > 0 and total_steps % self.sde_sample_freq == 0:
                     # Sample a new noise matrix
                     self.actor.reset_noise()
 

stable_baselines3/version.txt

@@ -1 +1 @@
-0.6.0a9
+0.6.0a10