Merge branch 'master' into feat/demo_refactoring

scripts/envs/open_manipulator/open_manipulator_reacher_env.py

@@ -1,9 +1,9 @@
 #! usr/bin/env python
 
-import numpy as np
-
 import gym
+import numpy as np
 from gym.utils import seeding
+
 from ros_interface import (
     OpenManipulatorRosGazeboInterface,
     OpenManipulatorRosRealInterface,
@@ -78,16 +78,15 @@ class OpenManipulatorReacherEnv(gym.Env):
             # TODO: Add termination condition
             # if self.ros_interface.check_for_termination():
             #     self.done = True
-            if self.ros_interface.check_for_success():
+            if (
+                self.ros_interface.check_for_success()
+                or self.episode_steps == self._max_episode_steps
+            ):
                 self.done = True
                 self.episode_steps = 0
 
         obs = self.ros_interface.get_observation()
 
-        if self.episode_steps == self._max_episode_steps:
-            self.done = False
-            self.episode_steps = 0
-
         return obs, self.reward_rescale_ratio * self.reward, self.done, None
 
     def reset(self):

scripts/envs/open_manipulator/ros_interface.py

@@ -6,6 +6,8 @@ from math import cos, sin
 
 import gym
 import numpy as np
+
+import rospkg  # noqa
 import rospy  # noqa
 import tf  # noqa
 import tf.transformations as tr  # noqa
@@ -16,8 +18,6 @@ from sensor_msgs.msg import JointState
 from std_msgs.msg import Float64
 from urdf_parser_py.urdf import URDF  # noqa
 
-import rospkg  # noqa
-
 
 class OpenManipulatorRosBaseInterface(object):
     """Open Manipulator Interface based on ROS."""