unified API wrapper and updated examples

alr_envs/classic_control/hole_reacher/hole_reacher.py

@@ -69,9 +69,17 @@ class HoleReacherEnv(gym.Env):
     def dt(self) -> Union[float, int]:
         return self._dt
 
+    # @property
+    # def start_pos(self):
+    #     return self._start_pos
+
     @property
-    def start_pos(self):
-        return self._start_pos
+    def current_pos(self):
+        return self._joint_angles.copy()
+
+    @property
+    def current_vel(self):
+        return self._angle_velocity.copy()
 
     def step(self, action: np.ndarray):
         """

alr_envs/classic_control/hole_reacher/hole_reacher_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 HoleReacherMPWrapper(MPEnvWrapper):
@@ -19,11 +19,15 @@ class HoleReacherMPWrapper(MPEnvWrapper):
         ])
 
     @property
-    def start_pos(self) -> Union[float, int, np.ndarray]:
-        return self.env.start_pos
+    def current_pos(self) -> Union[float, int, np.ndarray, Tuple]:
+        return self.env.current_pos
 
     @property
-    def goal_pos(self) -> Union[float, int, np.ndarray]:
+    def current_vel(self) -> Union[float, int, np.ndarray, Tuple]:
+        return self.env.current_vel
+
+    @property
+    def goal_pos(self) -> Union[float, int, np.ndarray, Tuple]:
         raise ValueError("Goal position is not available and has to be learnt based on the environment.")
 
     @property

alr_envs/classic_control/simple_reacher/simple_reacher.py

@@ -59,9 +59,17 @@ class SimpleReacherEnv(gym.Env):
     def dt(self) -> Union[float, int]:
         return self._dt
 
+    # @property
+    # def start_pos(self):
+    #     return self._start_pos
+
     @property
-    def start_pos(self):
-        return self._start_pos
+    def current_pos(self):
+        return self._joint_angles
+
+    @property
+    def current_vel(self):
+        return self._angle_velocity
 
     def step(self, action: np.ndarray):
         """

alr_envs/classic_control/simple_reacher/simple_reacher_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 SimpleReacherMPWrapper(MPEnvWrapper):
@@ -17,11 +17,15 @@ class SimpleReacherMPWrapper(MPEnvWrapper):
         ])
 
     @property
-    def start_pos(self):
-        return self.env.start_pos
+    def current_pos(self) -> Union[float, int, np.ndarray, Tuple]:
+        return self.env.current_pos
 
     @property
-    def goal_pos(self):
+    def current_vel(self) -> Union[float, int, np.ndarray, Tuple]:
+        return self.env.current_vel
+
+    @property
+    def goal_pos(self) -> Union[float, int, np.ndarray, Tuple]:
         raise ValueError("Goal position is not available and has to be learnt based on the environment.")
 
     @property

alr_envs/classic_control/viapoint_reacher/viapoint_reacher.py

@@ -63,9 +63,17 @@ class ViaPointReacher(gym.Env):
     def dt(self):
         return self._dt
 
+    # @property
+    # def start_pos(self):
+    #     return self._start_pos
+
     @property
-    def start_pos(self):
-        return self._start_pos
+    def current_pos(self):
+        return self._joint_angles.copy()
+
+    @property
+    def current_vel(self):
+        return self._angle_velocity.copy()
 
     def step(self, action: np.ndarray):
         """

alr_envs/classic_control/viapoint_reacher/viapoint_reacher_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 ViaPointReacherMPWrapper(MPEnvWrapper):
@@ -18,11 +18,15 @@ class ViaPointReacherMPWrapper(MPEnvWrapper):
         ])
 
     @property
-    def start_pos(self) -> Union[float, int, np.ndarray]:
-        return self.env.start_pos
+    def current_pos(self) -> Union[float, int, np.ndarray, Tuple]:
+        return self.env.current_pos
 
     @property
-    def goal_pos(self) -> Union[float, int, np.ndarray]:
+    def current_vel(self) -> Union[float, int, np.ndarray, Tuple]:
+        return self.env.current_vel
+
+    @property
+    def goal_pos(self) -> Union[float, int, np.ndarray, Tuple]:
         raise ValueError("Goal position is not available and has to be learnt based on the environment.")
 
     @property