Fix: Some fancy envs failed determinism test because they sampled during reset before the random gen was seeded

fancy_gym/envs/mujoco/ant_jump/ant_jump.py

@@ -162,8 +162,9 @@ class AntJumpEnv(AntEnvCustomXML):
         self.current_step = 0
         self.max_height = 0
         # goal heights from 1.0 to 2.5; can be increased, but didnt work well with CMORE
+        ret = super().reset(seed=seed, options=options)
         self.goal = self.np_random.uniform(1.0, 2.5, 1)
-        return super().reset(seed=seed, options=options)
+        return ret
 
     # reset_model had to be implemented in every env to make it deterministic
     def reset_model(self):

fancy_gym/envs/mujoco/half_cheetah_jump/half_cheetah_jump.py

@@ -127,8 +127,9 @@ class HalfCheetahJumpEnv(HalfCheetahEnvCustomXML):
             -> Tuple[ObsType, Dict[str, Any]]:
         self.max_height = 0
         self.current_step = 0
+        ret = super().reset(seed=seed, options=options)
         self.goal = self.np_random.uniform(1.1, 1.6, 1)  # 1.1 1.6
-        return super().reset(seed=seed, options=options)
+        return ret
 
     # overwrite reset_model to make it deterministic
     def reset_model(self):

fancy_gym/envs/mujoco/hopper_jump/hopper_jump_on_box.py

@@ -150,10 +150,11 @@ class HopperJumpOnBoxEnv(HopperEnvCustomXML):
         self.min_distance = 5000
         self.current_step = 0
         self.hopper_on_box = False
+        ret = super().reset(seed=seed, options=options)
         if self.context:
             self.box_x = self.np_random.uniform(1, 3, 1)
             self.model.body("box").pos = [self.box_x[0], 0, 0]
-        return super().reset(seed=seed, options=options)
+        return ret
 
     # overwrite reset_model to make it deterministic
     def reset_model(self):

fancy_gym/envs/mujoco/hopper_throw/hopper_throw.py

@@ -100,8 +100,9 @@ class HopperThrowEnv(HopperEnvCustomXML):
     def reset(self, *, seed: Optional[int] = None, options: Optional[Dict[str, Any]] = None) \
             -> Tuple[ObsType, Dict[str, Any]]:
         self.current_step = 0
+        ret = super().reset(seed=seed, options=options)
         self.goal = self.goal = self.np_random.uniform(2.0, 6.0, 1)  # 0.5 8.0
-        return super().reset(seed=seed, options=options)
+        return ret
 
     # overwrite reset_model to make it deterministic
     def reset_model(self):

fancy_gym/envs/mujoco/hopper_throw/hopper_throw_in_basket.py

@@ -130,10 +130,11 @@ class HopperThrowInBasketEnv(HopperEnvCustomXML):
 
         self.current_step = 0
         self.ball_in_basket = False
+        ret = super().reset(seed=seed, options=options)
         if self.context:
             self.basket_x = self.np_random.uniform(low=3, high=7, size=1)
             self.model.body("basket_ground").pos[:] = [self.basket_x[0], 0, 0]
-        return super().reset(seed=seed, options=options)
+        return ret
 
     # overwrite reset_model to make it deterministic
     def reset_model(self):

fancy_gym/envs/mujoco/walker_2d_jump/walker_2d_jump.py

@@ -152,8 +152,9 @@ class Walker2dJumpEnv(Walker2dEnvCustomXML):
             -> Tuple[ObsType, Dict[str, Any]]:
         self.current_step = 0
         self.max_height = 0
+        ret = super().reset(seed=seed, options=options)
         self.goal = self.np_random.uniform(1.5, 2.5, 1)  # 1.5 3.0
-        return super().reset(seed=seed, options=options)
+        return ret
 
     # overwrite reset_model to make it deterministic
     def reset_model(self):