env.__str__(); reverted reward to old original: -2 + vel - angle

gym_ultrasonic/envs/obstacle.py

@@ -71,6 +71,12 @@ def set_position(self, position):
         """
         self.position = np.array(position, dtype=np.float32)
 
+    def __str__(self):
+        return f"{self.__class__.__name__}({self.extra_repr()})"
+
+    def extra_repr(self):
+        return f"{self.width} x {self.height}"
+
 
 class _Servo(Obstacle):
     """
@@ -133,6 +139,9 @@ def reset(self):
         self.ccw = 1
         self.angle = 0
 
+    def extra_repr(self):
+        return f"angle_range={self.angle_range}, angular_vel={self.angular_vel}"
+
 
 class Robot(Obstacle):
     """
@@ -291,3 +300,6 @@ def reset(self, box):
         self.position = box.sample()
         self.angle = random.randint(0, 360)
         self.servo.reset()
+
+    def extra_repr(self):
+        return f"{super().extra_repr()} with a {self.servo}"

gym_ultrasonic/envs/ultrasonic_servo_env.py

@@ -136,7 +136,7 @@ def reward(self, move_step, angle_turn, servo_turn):
         """
         if self.robot.collision(self.obstacles):
             return -1000, True
-        reward = move_step - 3 * abs(angle_turn)
+        reward = -2 + move_step - abs(angle_turn)
         if servo_turn is not None:
             reward -= abs(servo_turn)
         return reward, False
@@ -214,3 +214,8 @@ def render(self, mode='human'):
         self.servo_transform.set_rotation(math.radians(self.robot.servo.angle))
         with_rgb = mode == 'rgb_array'
         return self.viewer.render(return_rgb_array=with_rgb)
+
+    def __str__(self):
+        return f"{super().__str__()}:\nobservation_space={self.observation_space.low, self.observation_space.high};" \
+               f"\naction_space={self.action_space.low, self.action_space.high};" \
+               f"\n{self.robot}"