Updated custom policy docs (#1067)

This commit is contained in:
Alex Pasquali 2022-09-18 09:17:57 +02:00 committed by GitHub
parent 440735cbd0
commit d0b129ecc3
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 6 additions and 4 deletions

View file

@ -95,9 +95,10 @@ that derives from ``BaseFeaturesExtractor`` and then pass it to the model when t
.. note::
By default the feature extractor is shared between the actor and the critic to save computation (when applicable).
However, this can be changed by defining a custom policy for on-policy algorithms or setting
``share_features_extractor=False`` in the ``policy_kwargs`` for off-policy algorithms
(and when applicable).
However, this can be changed by defining a custom policy for on-policy algorithms
(see `issue #1066 <https://github.com/DLR-RM/stable-baselines3/issues/1066#issuecomment-1246866844>`_
for more information) or setting ``share_features_extractor=False`` in the
``policy_kwargs`` for off-policy algorithms (and when applicable).
.. code-block:: python

View file

@ -49,6 +49,7 @@ Documentation:
- Fixed typo in ppo doc (@francescoluciano)
- Fixed typo in install doc(@jlp-ue)
- Clarified and standardized verbosity documentation
- Added link to a GitHub issue in the custom policy documentation (@AlexPasqua)
Release 1.6.0 (2022-07-11)
@ -1037,4 +1038,4 @@ And all the contributors:
@simoninithomas @armandpl @manuel-delverme @Gautam-J @gianlucadecola @buoyancy99 @caburu @xy9485
@Gregwar @ycheng517 @quantitative-technologies @bcollazo @git-thor @TibiGG @cool-RR @MWeltevrede
@Melanol @qgallouedec @francescoluciano @jlp-ue @burakdmb @timothe-chaumont @honglu2875
@anand-bala @hughperkins @sidney-tio
@anand-bala @hughperkins @sidney-tio @AlexPasqua