updates on mp wrappers and some bugfixes

alr_envs/classic_control/hole_reacher.py

@@ -7,10 +7,10 @@ from gym.utils import seeding
 from matplotlib import patches
 
 from alr_envs.classic_control.utils import check_self_collision
-from alr_envs.utils.mps.mp_environments import MPEnv
+from alr_envs.utils.mps.mp_environments import AlrEnv
 
 
-class HoleReacherEnv(MPEnv):
+class HoleReacherEnv(AlrEnv):
 
     def __init__(self, n_links: int, hole_x: Union[None, float] = None, hole_depth: Union[None, float] = None,
                  hole_width: float = 1., random_start: bool = False, allow_self_collision: bool = False,
@@ -71,11 +71,11 @@ class HoleReacherEnv(MPEnv):
         A single step with an action in joint velocity space
         """
 
+        acc = (action - self._angle_velocity) / self.dt
         self._angle_velocity = action
         self._joint_angles = self._joint_angles + self.dt * self._angle_velocity
         self._update_joints()
 
-        acc = (action - self._angle_velocity) / self.dt
         reward, info = self._get_reward(acc)
 
         info.update({"is_collided": self._is_collided})

alr_envs/classic_control/simple_reacher.py

@@ -5,10 +5,10 @@ import numpy as np
 from gym import spaces
 from gym.utils import seeding
 
-from alr_envs.utils.mps.mp_environments import MPEnv
+from alr_envs.utils.mps.mp_environments import AlrEnv
 
 
-class SimpleReacherEnv(MPEnv):
+class SimpleReacherEnv(AlrEnv):
     """
     Simple Reaching Task without any physics simulation.
     Returns no reward until 150 time steps. This allows the agent to explore the space, but requires precise actions

alr_envs/classic_control/viapoint_reacher.py

@@ -6,10 +6,10 @@ import numpy as np
 from gym.utils import seeding
 
 from alr_envs.classic_control.utils import check_self_collision
-from alr_envs.utils.mps.mp_environments import MPEnv
+from alr_envs.utils.mps.mp_environments import AlrEnv
 
 
-class ViaPointReacher(MPEnv):
+class ViaPointReacher(AlrEnv):
 
     def __init__(self, n_links, random_start: bool = True, via_target: Union[None, Iterable] = None,
                  target: Union[None, Iterable] = None, allow_self_collision=False, collision_penalty=1000):