How to use the learn2learn.gym.envs.meta_env.MetaEnv function in learn2learn

#!/usr/bin/env python3

import gym
import numpy as np
from gym.envs.mujoco.mujoco_env import MujocoEnv

from learn2learn.gym.envs.meta_env import MetaEnv


class AntDirectionEnv(MetaEnv, MujocoEnv, gym.utils.EzPickle):
    """
    [[Source]](https://github.com/learnables/learn2learn/blob/master/learn2learn/gym/envs/mujoco/ant_direction.py)

    **Description**

    This environment requires the Ant to learn to run in a random direction in the
    XY plane. At each time step the ant receives a signal composed of a
    control cost and a reward equal to its average velocity in the direction
    of the plane. The tasks are 2d-arrays sampled uniformly along the unit circle.
    The target direction is indicated by the vector from the origin to the sampled point.
    The velocity is calculated as the distance (in the target direction) of the ant's torso
    position before and after taking the specified action divided by a small value dt.
    As noted in [1], a small positive bonus is added to the reward to stop the ant from
    prematurely ending the episode.

    **Credit**

#!/usr/bin/env python3

import numpy as np
from gym import spaces
from gym.utils import seeding

from learn2learn.gym.envs.meta_env import MetaEnv


class Particles2DEnv(MetaEnv):
    """
    [[Source]](https://github.com/learnables/learn2learn/blob/master/learn2learn/gym/envs/particles/particles_2d.py)

    **Description**

    Each task is defined by the location of the goal. A point mass
    receives a directional force and moves accordingly 
    (clipped in [-0.1,0.1]). The reward is equal to the negative
    distance from the goal.

    **Credit**

    Adapted from Jonas Rothfuss' implementation.

    """

#!/usr/bin/env python3

import gym
import numpy as np
from gym.envs.mujoco.mujoco_env import MujocoEnv

from learn2learn.gym.envs.meta_env import MetaEnv


class AntForwardBackwardEnv(MetaEnv, MujocoEnv, gym.utils.EzPickle):
    """
    [[Source]](https://github.com/learnables/learn2learn/blob/master/learn2learn/gym/envs/mujoco/ant_forward_backward.py)

    **Description**

    This environment requires the ant to learn to run forward or backward.
    At each time step the ant receives a signal composed of a
    control cost and a reward equal to its average velocity in the direction
    of the plane. The tasks are Bernoulli samples on {-1, 1} with probability 0.5, where -1 indicates the ant should
    move backward and +1 indicates the ant should move forward.
    The velocity is calculated as the distance (in the direction of the plane) of the ant's torso
    position before and after taking the specified action divided by a small value dt.
    As noted in [1], a small positive bonus is added to the reward to stop the ant from
    prematurely ending the episode.

    **Credit**

#!/usr/bin/env python3

import gym
import numpy as np
from gym.envs.mujoco.mujoco_env import MujocoEnv

from learn2learn.gym.envs.meta_env import MetaEnv


def mass_center(model, sim):
    mass = np.expand_dims(model.body_mass, 1)
    xpos = sim.data.xipos
    return (np.sum(mass * xpos, 0) / np.sum(mass))


class HumanoidDirectionEnv(MetaEnv, MujocoEnv, gym.utils.EzPickle):
    """
    [[Source]](https://github.com/learnables/learn2learn/blob/master/learn2learn/gym/envs/mujoco/humanoid_direction.py)

    **Description**

    This environment requires the humanoid to learn to run in a random direction in the
    XY plane. At each time step the humanoid receives a signal composed of a
    control cost and a reward equal to its average velocity in the target direction.
    The tasks are 2d-arrays sampled uniformly along the unit circle.
    The target direction is indicated by the vector from the origin to the sampled point.
    The velocity is calculated as the distance (in the target direction) of the humanoid's torso
    position before and after taking the specified action divided by a small value dt.
    A small positive bonus is added to the reward to stop the humanoid from
    prematurely ending the episode.

    **Credit**

#!/usr/bin/env python3

import gym
import numpy as np
from gym.envs.mujoco.mujoco_env import MujocoEnv

from learn2learn.gym.envs.meta_env import MetaEnv


class HalfCheetahForwardBackwardEnv(MetaEnv, MujocoEnv, gym.utils.EzPickle):
    """
    [[Source]](https://github.com/learnables/learn2learn/blob/master/learn2learn/gym/envs/mujoco/halfcheetah_forward_backward.py)

    **Description**

    This environment requires the half-cheetah to learn to run forward or backward.
    At each time step the half-cheetah receives a signal composed of a
    control cost and a reward equal to its average velocity in the direction
    of the plane. The tasks are Bernoulli samples on {-1, 1} with probability 0.5, where -1 indicates the half-cheetah should
    move backward and +1 indicates the half-cheetah should move forward.
    The velocity is calculated as the distance (in the target direction) of the half-cheetah's torso
    position before and after taking the specified action divided by a small value dt.

    **Credit**

    Adapted from Jonas Rothfuss' implementation.