Update docstring on MlpExtractor. Resolves #736 (#774)

* Improve docstring on MlpExtractor.

* update changelog.
This commit is contained in:
Gianluca De Cola 2022-02-16 00:50:17 +01:00 committed by GitHub
parent 59bec30180
commit 58a98060f9
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 6 additions and 3 deletions

View file

@ -40,6 +40,7 @@ Documentation:
- Added doc on Hugging Face integration (@simoninithomas)
- Added furuta pendulum project to project list (@armandpl)
- Fix indentation 2 spaces to 4 spaces in custom env documentation example (@Gautam-J)
- Update MlpExtractor docstring (@gianlucadecola)
Release 1.4.0 (2022-01-18)
@ -919,4 +920,4 @@ And all the contributors:
@benblack769 @bstee615 @c-rizz @skandermoalla @MihaiAnca13 @davidblom603 @ayeright @cyprienc
@wkirgsn @AechPro @CUN-bjy @batu @IljaAvadiev @timokau @kachayev @cleversonahum
@eleurent @ac-93 @cove9988 @theDebugger811 @hsuehch @Demetrio92 @thomasgubler @IperGiove @ScheiklP
@simoninithomas @armandpl @manuel-delverme @Gautam-J
@simoninithomas @armandpl @manuel-delverme @Gautam-J @gianlucadecola

View file

@ -135,8 +135,10 @@ def create_mlp(
class MlpExtractor(nn.Module):
"""
Constructs an MLP that receives observations as an input and outputs a latent representation for the policy and
a value network. The ``net_arch`` parameter allows to specify the amount and size of the hidden layers and how many
Constructs an MLP that receives the output from a previous feature extractor (i.e. a CNN) or directly
the observations (if no feature extractor is applied) as an input and outputs a latent representation
for the policy and a value network.
The ``net_arch`` parameter allows to specify the amount and size of the hidden layers and how many
of them are shared between the policy network and the value network. It is assumed to be a list with the following
structure: