Minor edits

docs/guide/custom_policy.rst

@@ -325,7 +325,7 @@ If your task requires even more granular control over the policy/value architect
           last_layer_dim_pi: int = 64,
           last_layer_dim_vf: int = 64,
       ):
-          super(CustomNetwork, self).__init__()
+          super().__init__()
 
           # IMPORTANT:
           # Save output dimensions, used to create the distributions
@@ -361,8 +361,6 @@ If your task requires even more granular control over the policy/value architect
           observation_space: spaces.Space,
           action_space: spaces.Space,
           lr_schedule: Callable[[float], float],
-          net_arch: Optional[List[Union[int, Dict[str, List[int]]]]] = None,
-          activation_fn: Type[nn.Module] = nn.Tanh,
           *args,
           **kwargs,
       ):
@@ -371,8 +369,6 @@ If your task requires even more granular control over the policy/value architect
               observation_space,
               action_space,
               lr_schedule,
-              net_arch,
-              activation_fn,
               # Pass remaining arguments to base class
               *args,
               **kwargs,

stable_baselines3/common/torch_layers.py

@@ -161,8 +161,8 @@ class MlpExtractor(nn.Module):
        It is formatted like ``dict(vf=[<value layer sizes>], pi=[<policy layer sizes>])``.
        If it is missing any of the keys (pi or vf), no non-shared layers (empty list) is assumed.
 
-    Depredcation note: shared layers in ``net_arch`` are deprecated, please use separate
-    pi and vf networks (e.g. net_arch=[dict(pi=[...], vf=[...])])
+    Deprecation note: shared layers in ``net_arch`` are deprecated, please use separate
+    pi and vf networks (e.g. net_arch=dict(pi=[...], vf=[...]))
 
     For example to construct a network with one shared layer of size 55 followed by two non-shared layers for the value
     network of size 255 and a single non-shared layer of size 128 for the policy network, the following layers_spec

tests/test_custom_policy.py

@@ -23,7 +23,7 @@
 @pytest.mark.parametrize("model_class", [A2C, PPO])
 def test_flexible_mlp(model_class, net_arch):
     if isinstance(net_arch, list) and len(net_arch) > 0 and isinstance(net_arch[0], int):
-        with pytest.warns():
+        with pytest.warns(DeprecationWarning):
             _ = model_class("MlpPolicy", "CartPole-v1", policy_kwargs=dict(net_arch=net_arch), n_steps=64).learn(300)
     else:
         _ = model_class("MlpPolicy", "CartPole-v1", policy_kwargs=dict(net_arch=net_arch), n_steps=64).learn(300)