signature for compute_reward

qgallouedec · Jun 10, 2024 · ea82d34 · ea82d34
1 parent 0d17e18
commit ea82d34
Show file tree

Hide file tree

Showing 6 changed files with 6 additions and 6 deletions.
diff --git a/panda_gym/envs/tasks/flip.py b/panda_gym/envs/tasks/flip.py
@@ -82,7 +82,7 @@ def is_success(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info:
         d = angle_distance(achieved_goal, desired_goal)
         return np.array(d < self.distance_threshold, dtype=bool)
 
-    def compute_reward(self, achieved_goal, desired_goal, info: Dict[str, Any]) -> np.ndarray:
+    def compute_reward(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info: Dict[str, Any] = {}) -> np.ndarray:
         d = angle_distance(achieved_goal, desired_goal)
         if self.reward_type == "sparse":
             return -np.array(d > self.distance_threshold, dtype=np.float32)

diff --git a/panda_gym/envs/tasks/pick_and_place.py b/panda_gym/envs/tasks/pick_and_place.py
@@ -87,7 +87,7 @@ def is_success(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info:
         d = distance(achieved_goal, desired_goal)
         return np.array(d < self.distance_threshold, dtype=bool)
 
-    def compute_reward(self, achieved_goal, desired_goal, info: Dict[str, Any]) -> np.ndarray:
+    def compute_reward(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info: Dict[str, Any] = {}) -> np.ndarray:
         d = distance(achieved_goal, desired_goal)
         if self.reward_type == "sparse":
             return -np.array(d > self.distance_threshold, dtype=np.float32)

diff --git a/panda_gym/envs/tasks/push.py b/panda_gym/envs/tasks/push.py
@@ -89,7 +89,7 @@ def is_success(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info:
         d = distance(achieved_goal, desired_goal)
         return np.array(d < self.distance_threshold, dtype=bool)
 
-    def compute_reward(self, achieved_goal, desired_goal, info: Dict[str, Any]) -> np.ndarray:
+    def compute_reward(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info: Dict[str, Any] = {}) -> np.ndarray:
         d = distance(achieved_goal, desired_goal)
         if self.reward_type == "sparse":
             return -np.array(d > self.distance_threshold, dtype=np.float32)

diff --git a/panda_gym/envs/tasks/reach.py b/panda_gym/envs/tasks/reach.py
@@ -56,7 +56,7 @@ def is_success(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info:
         d = distance(achieved_goal, desired_goal)
         return np.array(d < self.distance_threshold, dtype=bool)
 
-    def compute_reward(self, achieved_goal, desired_goal, info: Dict[str, Any]) -> np.ndarray:
+    def compute_reward(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info: Dict[str, Any] = {}) -> np.ndarray:
         d = distance(achieved_goal, desired_goal)
         if self.reward_type == "sparse":
             return -np.array(d > self.distance_threshold, dtype=np.float32)

diff --git a/panda_gym/envs/tasks/slide.py b/panda_gym/envs/tasks/slide.py
@@ -93,7 +93,7 @@ def is_success(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info:
         d = distance(achieved_goal, desired_goal)
         return np.array(d < self.distance_threshold, dtype=bool)
 
-    def compute_reward(self, achieved_goal, desired_goal, info: Dict[str, Any]) -> np.ndarray:
+    def compute_reward(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info: Dict[str, Any] = {}) -> np.ndarray:
         d = distance(achieved_goal, desired_goal)
         if self.reward_type == "sparse":
             return -np.array(d > self.distance_threshold, dtype=np.float32)

diff --git a/panda_gym/envs/tasks/stack.py b/panda_gym/envs/tasks/stack.py
@@ -122,7 +122,7 @@ def is_success(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info:
         d = distance(achieved_goal, desired_goal)
         return np.array((d < self.distance_threshold), dtype=bool)
 
-    def compute_reward(self, achieved_goal, desired_goal, info: Dict[str, Any]) -> np.ndarray:
+    def compute_reward(self, achieved_goal: np.ndarray, desired_goal: np.ndarray, info: Dict[str, Any] = {}) -> np.ndarray:
         d = distance(achieved_goal, desired_goal)
         if self.reward_type == "sparse":
             return -np.array((d > self.distance_threshold), dtype=np.float32)