Add pydoc on how to map the multi-objective reward to the original gy…

…mnasium reward (#92)

mo_gymnasium/envs/mujoco/ant.py

@@ -11,6 +11,11 @@ class MOAntEnv(AntEnv, EzPickle):
 
     See [Gymnasium's env](https://gymnasium.farama.org/environments/mujoco/ant/) for more information.
 
+    The original Gymnasium's 'Ant-v4' is recovered by the following linear scalarization:
+
+    env = mo_gym.make('mo-ant-v4', cost_objective=False)
+    LinearReward(env, weight=np.array([1.0, 0.0]))
+
     ## Reward Space
     The reward is 2- or 3-dimensional:
     - 0: x-velocity

mo_gymnasium/envs/mujoco/half_cheetah.py

@@ -11,6 +11,11 @@ class MOHalfCheehtahEnv(HalfCheetahEnv, EzPickle):
 
     See [Gymnasium's env](https://gymnasium.farama.org/environments/mujoco/half_cheetah/) for more information.
 
+    The original Gymnasium's 'HalfCheetah-v4' is recovered by the following linear scalarization:
+
+    env = mo_gym.make('mo-halfcheetah-v4')
+    LinearReward(env, weight=np.array([1.0, 1.0]))
+
     ## Reward Space
     The reward is 2-dimensional:
     - 0: Reward for running forward

mo_gymnasium/envs/mujoco/hopper.py

@@ -11,6 +11,11 @@ class MOHopperEnv(HopperEnv, EzPickle):
 
     See [Gymnasium's env](https://gymnasium.farama.org/environments/mujoco/hopper/) for more information.
 
+    The original Gymnasium's 'Hopper-v4' is recovered by the following linear scalarization:
+
+    env = mo_gym.make('mo-hopper-v4', cost_objective=False)
+    LinearReward(env, weight=np.array([1.0, 0.0]))
+
     ## Reward Space
     The reward is 3-dimensional:
     - 0: Reward for going forward on the x-axis

mo_gymnasium/envs/mujoco/swimmer.py

@@ -11,6 +11,11 @@ class MOSwimmerEnv(SwimmerEnv, EzPickle):
 
     See [Gymnasium's env](https://gymnasium.farama.org/environments/mujoco/swimmer/) for more information.
 
+    The original Gymnasium's 'Swimmer-v4' is recovered by the following linear scalarization:
+
+    env = mo_gym.make('mo-swimmer-v4')
+    LinearReward(env, weight=np.array([1.0, 1e-4]))
+
     ## Reward Space
     The reward is 2-dimensional:
     - 0: Reward for moving forward (x-velocity)