Reworked cost and goal_met logic

src/encoder_shield_adpt_shield.py

@@ -387,7 +387,7 @@ class Encoder_DDPG_Adpt_Shield():
                     avg_goal_reaches += 1
                 
                 # Check for crash
-                elif cost > 0:
+                if cost > 0:
                     avg_safety_violations += 1
                     done = True
                     break
@@ -467,21 +467,21 @@ class Encoder_DDPG_Adpt_Shield():
                 self.update_target(self.target_actor.variables, self.actor.variables)
                 self.update_target(self.target_critic.variables, self.critic.variables)
                 total_updates += 1
-
-                # check for goal reach
-                if info.get('goal_met', False):
-                    episode_goal_reaches += 1
-                    self.safe_observations.append((prev_state, action))
                 
                 # check for crash
-                elif cost > 0:
+                if cost > 0:
                     episode_safety_violations += 1
                     self.unsafe_observations.append((prev_state, action))
                     done = True
                     break
 
+                # check for goal reach
+                elif info.get('goal_met', False):
+                    episode_goal_reaches += 1
+                    self.safe_observations.append((prev_state, action))
+
                 # save the init step
-                if (episode_steps-1 == 0) and cost == 0:
+                elif episode_steps-1 == 0:
                    self.safe_observations.append((prev_state, action))
 
                 prev_state = next_state