Release 2.4.0

docs/guide/custom_policy.rst

@@ -36,9 +36,10 @@ You can also easily define a custom architecture for the policy (or value) netwo
 
 .. note::
 
-	Defining a custom policy class is equivalent to passing ``policy_kwargs``. However,
-  it lets you name the policy and so makes usually the code clearer. ``policy_kwargs`` should be rather used
-  when doing hyperparameter search.
+    Defining a custom policy class is equivalent to passing ``policy_kwargs``.
+    However, it lets you name the policy and so makes usually the code clearer.
+    ``policy_kwargs`` should be rather used when doing hyperparameter search.
+
 
 
 .. code-block:: python
@@ -74,7 +75,8 @@ You can also easily define a custom architecture for the policy (or value) netwo
 
 .. warning::
 
-  When loading a model with a custom policy, you must pass the custom policy explicitly when loading the model. (cf previous example)
+    When loading a model with a custom policy, you must pass the custom policy explicitly when loading the model.
+    (cf previous example)
 
 
 You can also register your policy, to help with code simplicity: you can refer to your custom policy using a string.

docs/misc/changelog.rst

@@ -5,9 +5,17 @@ Changelog
 
 For download links, please look at `Github release page <https://github.com/hill-a/stable-baselines/releases>`_.
 
-Pre-Release 2.4.0a (WIP)
+Pre-Release 2.4.1 (WIP)
 --------------------------
 
+
+
+
+Release 2.4.0 (2019-01-17)
+--------------------------
+
+**Soft Actor-Critic (SAC) and policy kwargs**
+
 - added Soft Actor-Critic (SAC) model
 - fixed a bug in DQN where prioritized_replay_beta_iters param was not used
 - fixed DDPG that did not save target network parameters

setup.py

@@ -112,7 +112,7 @@
       license="MIT",
       long_description=long_description,
       long_description_content_type='text/markdown',
-      version="2.4.0a",
+      version="2.4.0",
       )
 
 # python setup.py sdist

stable_baselines/__init__.py

@@ -12,7 +12,7 @@
 from stable_baselines.trpo_mpi import TRPO
 from stable_baselines.sac import SAC
 
-__version__ = "2.4.0a"
+__version__ = "2.4.0"
 
 
 # patch Gym spaces to add equality functions, if not implemented