unified API wrapper and updated examples

alr_envs/dmc/Ball_in_the_cup_mp_wrapper.py

@@ -1,27 +0,0 @@
-from typing import Union
-
-import numpy as np
-
-from mp_env_api.env_wrappers.mp_env_wrapper import MPEnvWrapper
-
-
-class DMCBallInCupMPWrapper(MPEnvWrapper):
-
-    @property
-    def active_obs(self):
-        # Besides the ball position, the environment is always set to 0.
-        return np.hstack([
-            [False] * 2,  # cup position
-            [True] * 2,  # ball position
-            [False] * 2,  # cup velocity
-            [False] * 2,  # ball velocity
-        ])
-
-    @property
-    def start_pos(self) -> Union[float, int, np.ndarray]:
-        return np.hstack([self.physics.named.data.qpos['cup_x'], self.physics.named.data.qpos['cup_z']])
-
-    @property
-    def dt(self) -> Union[float, int]:
-        # Taken from: https://github.com/deepmind/dm_control/blob/master/dm_control/suite/ball_in_cup.py#L27
-        return 0.02

alr_envs/dmc/ball_in_cup/ball_in_the_cup_mp_wrapper.py

@@ -0,0 +1,34 @@
+from typing import Tuple, Union
+
+import numpy as np
+
+from mp_env_api.interface_wrappers.mp_env_wrapper import MPEnvWrapper
+
+
+class DMCBallInCupMPWrapper(MPEnvWrapper):
+
+    @property
+    def active_obs(self):
+        # Besides the ball position, the environment is always set to 0.
+        return np.hstack([
+            [False] * 2,  # cup position
+            [True] * 2,  # ball position
+            [False] * 2,  # cup velocity
+            [False] * 2,  # ball velocity
+        ])
+
+    @property
+    def current_pos(self) -> Union[float, int, np.ndarray]:
+        return np.hstack([self.physics.named.data.qpos['cup_x'], self.physics.named.data.qpos['cup_z']])
+
+    @property
+    def current_vel(self) -> Union[float, int, np.ndarray, Tuple]:
+        return np.hstack([self.physics.named.data.qvel['cup_x'], self.physics.named.data.qvel['cup_z']])
+
+    @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
+    def dt(self) -> Union[float, int]:
+        return self.env.dt