docs: Add policy documentation links to policy_kwargs parameter

stable_baselines3/a2c/a2c.py

@@ -48,7 +48,7 @@ class A2C(OnPolicyAlgorithm):
     :param stats_window_size: Window size for the rollout logging, specifying the number of episodes to average
         the reported success rate, mean episode length, and mean reward over
     :param tensorboard_log: the log location for tensorboard (if None, no logging)
-    :param policy_kwargs: additional arguments to be passed to the policy on creation
+    :param policy_kwargs: additional arguments to be passed to the policy on creation. See :ref:`a2c_policies`
     :param verbose: Verbosity level: 0 for no output, 1 for info messages (such as device or wrappers used), 2 for
         debug messages
     :param seed: Seed for the pseudo random generators

stable_baselines3/ddpg/ddpg.py

@@ -44,7 +44,7 @@ class DDPG(TD3):
     :param optimize_memory_usage: Enable a memory efficient variant of the replay buffer
         at a cost of more complexity.
         See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195
-    :param policy_kwargs: additional arguments to be passed to the policy on creation
+    :param policy_kwargs: additional arguments to be passed to the policy on creation. See :ref:`ddpg_policies`
     :param verbose: Verbosity level: 0 for no output, 1 for info messages (such as device or wrappers used), 2 for
         debug messages
     :param seed: Seed for the pseudo random generators

stable_baselines3/dqn/dqn.py

@@ -53,7 +53,7 @@ class DQN(OffPolicyAlgorithm):
     :param stats_window_size: Window size for the rollout logging, specifying the number of episodes to average
         the reported success rate, mean episode length, and mean reward over
     :param tensorboard_log: the log location for tensorboard (if None, no logging)
-    :param policy_kwargs: additional arguments to be passed to the policy on creation
+    :param policy_kwargs: additional arguments to be passed to the policy on creation. See :ref:`dqn_policies`
     :param verbose: Verbosity level: 0 for no output, 1 for info messages (such as device or wrappers used), 2 for
         debug messages
     :param seed: Seed for the pseudo random generators

stable_baselines3/ppo/ppo.py

@@ -62,7 +62,7 @@ class PPO(OnPolicyAlgorithm):
     :param stats_window_size: Window size for the rollout logging, specifying the number of episodes to average
         the reported success rate, mean episode length, and mean reward over
     :param tensorboard_log: the log location for tensorboard (if None, no logging)
-    :param policy_kwargs: additional arguments to be passed to the policy on creation
+    :param policy_kwargs: additional arguments to be passed to the policy on creation. See :ref:`ppo_policies`
     :param verbose: Verbosity level: 0 for no output, 1 for info messages (such as device or wrappers used), 2 for
         debug messages
     :param seed: Seed for the pseudo random generators

stable_baselines3/sac/sac.py

@@ -68,7 +68,7 @@ class SAC(OffPolicyAlgorithm):
     :param stats_window_size: Window size for the rollout logging, specifying the number of episodes to average
         the reported success rate, mean episode length, and mean reward over
     :param tensorboard_log: the log location for tensorboard (if None, no logging)
-    :param policy_kwargs: additional arguments to be passed to the policy on creation
+    :param policy_kwargs: additional arguments to be passed to the policy on creation. See :ref:`sac_policies`
     :param verbose: Verbosity level: 0 for no output, 1 for info messages (such as device or wrappers used), 2 for
         debug messages
     :param seed: Seed for the pseudo random generators

stable_baselines3/td3/td3.py

@@ -56,7 +56,7 @@ class TD3(OffPolicyAlgorithm):
     :param stats_window_size: Window size for the rollout logging, specifying the number of episodes to average
         the reported success rate, mean episode length, and mean reward over
     :param tensorboard_log: the log location for tensorboard (if None, no logging)
-    :param policy_kwargs: additional arguments to be passed to the policy on creation
+    :param policy_kwargs: additional arguments to be passed to the policy on creation. See :ref:`td3_policies`
     :param verbose: Verbosity level: 0 for no output, 1 for info messages (such as device or wrappers used), 2 for
         debug messages
     :param seed: Seed for the pseudo random generators