unified API wrapper and updated examples

alr_envs/mujoco/ball_in_a_cup/ball_in_a_cup.py

@@ -1,10 +1,11 @@
 from gym import utils
 import os
 import numpy as np
-from alr_envs.mujoco import alr_mujoco_env
+from gym.envs.mujoco import MujocoEnv
 
 
-class ALRBallInACupEnv(alr_mujoco_env.AlrMujocoEnv, utils.EzPickle):
+
+class ALRBallInACupEnv(MujocoEnv, utils.EzPickle):
     def __init__(self, n_substeps=4, apply_gravity_comp=True, simplified: bool = False,
                  reward_type: str = None, context: np.ndarray = None):
         utils.EzPickle.__init__(**locals())

alr_envs/mujoco/ball_in_a_cup/ball_in_a_cup_mp_wrapper.py

@@ -1,8 +1,8 @@
-from typing import Union
+from typing import Tuple, Union
 
 import numpy as np
 
-from mp_env_api.env_wrappers.mp_env_wrapper import MPEnvWrapper
+from mp_env_api.interface_wrappers.mp_env_wrapper import MPEnvWrapper
 
 
 class BallInACupMPWrapper(MPEnvWrapper):
@@ -24,6 +24,14 @@ class BallInACupMPWrapper(MPEnvWrapper):
         else:
             return self._start_pos
 
+    @property
+    def current_pos(self) -> Union[float, int, np.ndarray, Tuple]:
+        return self.sim.data.qpos[0:7].copy()
+
+    @property
+    def current_vel(self) -> Union[float, int, np.ndarray, Tuple]:
+        return self.sim.data.qvel[0:7].copy()
+
     @property
     def goal_pos(self):
         # TODO: @Max I think the default value of returning to the start is reasonable here

alr_envs/mujoco/ball_in_a_cup/ball_in_a_cup_positional_wrapper.py

@@ -1,15 +0,0 @@
-from typing import Tuple, Union
-
-import numpy as np
-
-from mp_env_api.env_wrappers.positional_env_wrapper import PositionalEnvWrapper
-
-
-class BallInACupPositionalWrapper(PositionalEnvWrapper):
-    @property
-    def current_pos(self) -> Union[float, int, np.ndarray, Tuple]:
-        return self.sim.data.qpos[0:7].copy()
-
-    @property
-    def current_vel(self) -> Union[float, int, np.ndarray, Tuple]:
-        return self.sim.data.qvel[0:7].copy()