add docstrings

ml-agents-envs/mlagents_envs/base_env.py

 
     @property
     def discrete_branches(self) -> Tuple[int, ...]:
+        """
+        Returns a Tuple of int corresponding to the number of possible actions
+        for each branch (only for discrete actions). Will return None in
+        for continuous actions.
+        """
+        """
+        Returns a an int corresponding to the number of discrete branches.
+        """
+        """
+        Returns a an int corresponding to the number of continuous actions.
+        """
+        """
+        Generates a numpy array corresponding to an empty action (all zeros)
+        for a number of agents.
+        :param n_agents: The number of agents that will have actions generated
+        """
+        """
+        Generates a numpy array corresponding to a random action (either discrete
+        or continuous) for a number of agents.
+        :param n_agents: The number of agents that will have actions generated
+        """
         if self.is_continuous():
             action = np.random.uniform(
                 low=-1.0, high=1.0, size=(n_agents, self.continuous_size)

ml-agents/mlagents/trainers/tests/tensorflow/test_simple_rl.py

         PPO_TF_CONFIG,
         hyperparameters=new_hyperparams,
         network_settings=new_networksettings,
-        max_steps=500,
+        max_steps=450,
         summary_freq=100,
         framework=FrameworkType.TENSORFLOW,
     )