Remove epsilon

ml-agents/mlagents/trainers/agent_processor.py

                     action = take_action_outputs["action"][idx]
                     if self.policy.use_continuous_act:
                         action_pre = take_action_outputs["pre_action"][idx]
-                        epsilon = take_action_outputs["random_normal_epsilon"][idx]
-                        epsilon = None
                     action_probs = take_action_outputs["log_probs"][idx]
                     action_masks = stored_info.action_masks[idx]
                     prev_action = self.policy.retrieve_previous_action([agent_id])[0, :]
                         max_step=max_step,
                         agent_id=agent_id,
                         memory=memory,
-                        epsilon=epsilon,
                     )
                     # Add the value outputs if needed
                     self.experience_buffers[agent_id].append(experience)

ml-agents/mlagents/trainers/trajectory.py

     action_pre: np.ndarray  # TODO: Remove this
     action_mask: np.array
     prev_action: np.ndarray
-    epsilon: float
     max_step: bool
     memory: np.array
     agent_id: str
         if exp.action_pre is not None:
             actions_pre = exp.action_pre
             agent_buffer_trajectory["actions_pre"].append(actions_pre)
-        if exp.epsilon is not None:
-            epsilons = exp.epsilon
-            agent_buffer_trajectory["random_normal_epsilon"].append(epsilons)
+
         # value is a dictionary from name of reward to value estimate of the value head
         agent_buffer_trajectory["actions"].append(exp.action)
         agent_buffer_trajectory["action_probs"].append(exp.action_probs)