Added the possibility to pass a custom activation function through the policy_kwargs argument when creating the following models: TD3, SAC, DDPG and DQN (like in sablebaseline3).
Description
Taking inspiration from stablebaseline, I've put the common code of the critic under the sbx\common\policy.py file since the critic code both in the sac module and in td3 module was the same.
Minor changes to .gitignore and Makefile have been made.
Motivation and Context
[x] I have raised an issue to propose this change (#37 )
closes #37
Types of changes
[ ] Bug fix (non-breaking change which fixes an issue)
[x] New feature (non-breaking change which adds functionality)
[ ] Breaking change (fix or feature that would cause existing functionality to change)
Added the possibility to pass a custom activation function through the
policy_kwargs
argument when creating the following models:TD3
,SAC
,DDPG
andDQN
(like in sablebaseline3).Description
Taking inspiration from
stablebaseline
, I've put the common code of the critic under thesbx\common\policy.py
file since the critic code both in thesac
module and intd3
module was the same.Minor changes to
.gitignore
andMakefile
have been made.Motivation and Context
closes #37
Types of changes
Checklist:
make format
(required)make check-codestyle
andmake lint
(required)make pytest
andmake type
both pass. (required)make doc
(required)Note: You can run most of the checks using
make commit-checks
.Note: we are using a maximum length of 127 characters per line