Doc update (custom policy + fix her example) (#436)

docs/guide/custom_policy.rst

@@ -388,6 +388,11 @@ you only need to specify ``net_arch=[256, 256]`` (here, two hidden layers of 256
     between the actor and the critic are allowed (to prevent issues with target networks).
 
 
+.. note::
+    For advanced customization of off-policy algorithms policies, please take a look at the code.
+    A good understanding of the algorithm used is required, see discussion in `issue #425 <https://github.com/DLR-RM/stable-baselines3/issues/425>`_
+
+
 .. code-block:: python
 
   from stable_baselines3 import SAC

docs/guide/examples.rst

@@ -416,7 +416,7 @@ The parking env is a goal-conditioned continuous control task, in which the vehi
         # we have to manually specify the max number of steps per episode
         max_episode_length=100,
         online_sampling=True,
-      )
+      ),
       verbose=1,
       buffer_size=int(1e6),
       learning_rate=1e-3,

docs/misc/changelog.rst

@@ -70,7 +70,8 @@ Documentation:
 - Clarified pip installation in Zsh (@tom-doerr)
 - Clarified return computation for on-policy algorithms (TD(lambda) estimate was used)
 - Added example for using ``ProcgenEnv``
-
+- Added note about advanced custom policy example for off-policy algorithms
+- Fixed DQN unicode checkmarks
 
 Release 1.0 (2021-03-15)
 ------------------------

docs/modules/dqn.rst

@@ -41,11 +41,11 @@ Can I use?
 ============= ====== ===========
 Space         Action Observation
 ============= ====== ===========
-Discrete      ✔      ✔
-Box           ❌      ✔
-MultiDiscrete ❌      ✔
-MultiBinary   ❌      ✔
-Dict          ❌     ✔️
+Discrete      ✔️      ✔️
+Box           ❌      ✔️
+MultiDiscrete ❌      ✔️
+MultiBinary   ❌      ✔️
+Dict          ❌      ✔️️
 ============= ====== ===========