How to use the gym.utils.EzPickle.__init__ function in gym

self.obj_b_sid = 0
        self.tar_t_sid = 0
        self.tar_b_sid = 0
        self.pen_length = 1.0
        self.tar_length = 1.0

        curr_dir = os.path.dirname(os.path.abspath(__file__))
        mujoco_env.MujocoEnv.__init__(self, curr_dir+'/assets/DAPG_pen.xml', 5)

        # change actuator sensitivity
        self.sim.model.actuator_gainprm[self.sim.model.actuator_name2id('A_WRJ1'):self.sim.model.actuator_name2id('A_WRJ0')+1,:] = np.array([10, 0, 0])
        self.sim.model.actuator_gainprm[self.sim.model.actuator_name2id('A_FFJ3'):self.sim.model.actuator_name2id('A_THJ0')+1,:] = np.array([1, 0, 0])
        self.sim.model.actuator_biasprm[self.sim.model.actuator_name2id('A_WRJ1'):self.sim.model.actuator_name2id('A_WRJ0')+1,:] = np.array([0, -10, 0])
        self.sim.model.actuator_biasprm[self.sim.model.actuator_name2id('A_FFJ3'):self.sim.model.actuator_name2id('A_THJ0')+1,:] = np.array([0, -1, 0])

        utils.EzPickle.__init__(self)
        self.target_obj_bid = self.sim.model.body_name2id("target")
        self.S_grasp_sid = self.sim.model.site_name2id('S_grasp')
        self.obj_bid = self.sim.model.body_name2id('Object')
        self.eps_ball_sid = self.sim.model.site_name2id('eps_ball')
        self.obj_t_sid = self.sim.model.site_name2id('object_top')
        self.obj_b_sid = self.sim.model.site_name2id('object_bottom')
        self.tar_t_sid = self.sim.model.site_name2id('target_top')
        self.tar_b_sid = self.sim.model.site_name2id('target_bottom')

        self.pen_length = np.linalg.norm(self.data.site_xpos[self.obj_t_sid] - self.data.site_xpos[self.obj_b_sid])
        self.tar_length = np.linalg.norm(self.data.site_xpos[self.tar_t_sid] - self.data.site_xpos[self.tar_b_sid])

        self.act_mid = np.mean(self.model.actuator_ctrlrange, axis=1)
        self.act_rng = 0.5*(self.model.actuator_ctrlrange[:,1]-self.model.actuator_ctrlrange[:,0])

def __init__(self,
                 goal_reward=10,
                 actuation_cost_coeff=30.0,
                 distance_cost_coeff=1.0,
                 init_sigma=0.1):
        EzPickle.__init__(**locals())

        self.dynamics = PointDynamics(dim=2, sigma=0)
        self.init_mu = np.zeros(2, dtype=np.float32)
        self.init_sigma = init_sigma
        self.goal_positions = np.array(
            (
                (5, 0),
                (-5, 0),
                (0, 5),
                (0, -5)
            ),
            dtype=np.float32)
        self.goal_threshold = 1.0
        self.goal_reward = goal_reward
        self.action_cost_coeff = actuation_cost_coeff
        self.distance_cost_coeff = distance_cost_coeff

contype="1",
                    conaffinity="1",
                    condim="3",
                )




            _, file_path = tempfile.mkstemp(text=True)
            tree.write(file_path)

            # self._goal_range = self._find_goal_range()
            self._cached_segments = None
            # import pdb;pdb.set_trace()
            class_type.__init__(self, model_path=file_path)
            utils.EzPickle.__init__(self)

def __init__(self):
        utils.EzPickle.__init__(self)
        mujoco_env.MujocoEnv.__init__(self, 'ant_bandits.xml', 5)
        # self.realgoal = self.np_random.uniform(low=0, high=5, size=2)
        self.realgoal = np.array([5, 0]) if np.random.uniform() < 0.5 else np.array([0, 5])
        # self.realgoal = np.array([5, 0])

# data structure for modeling delays in observation and action
        self.observation_buffer = []
        self.action_buffer = []
        self.obs_delay = 0
        self.act_delay = 0

        self.cur_step = 0

        self.use_sparse_reward = False
        self.horizon = 999

        self.total_reward = 0

        mujoco_env.MujocoEnv.__init__(self, 'hopper.xml', 4)

        utils.EzPickle.__init__(self)

def __init__(self,
                 xml_file='half_cheetah.xml',
                 forward_reward_weight=1.0,
                 ctrl_cost_weight=0.1,
                 reset_noise_scale=0.1,
                 exclude_current_positions_from_observation=True):
        utils.EzPickle.__init__(**locals())

        self._forward_reward_weight = forward_reward_weight

        self._ctrl_cost_weight = ctrl_cost_weight

        self._reset_noise_scale = reset_noise_scale

        self._exclude_current_positions_from_observation = (
            exclude_current_positions_from_observation)

        mujoco_env.MujocoEnv.__init__(self, xml_file, 5)

def __init__(self, model_path=os.path.dirname(gym.envs.mujoco.__file__) + "/assets/pusher.xml", **kwargs):
        mujoco_env.MujocoEnv.__init__(self, model_path, 5)
        utils.EzPickle.__init__(self)

        # make sure we're using a proper OpenAI gym Mujoco Env
        assert isinstance(self, mujoco_env.MujocoEnv)

        self.model.jnt_range = self.get_and_modify_joint_range('r_shoulder_pan_joint')
        self.model._compute_subtree()
        self.model.forward()

def __init__(self):
        mujoco_env.MujocoEnv.__init__(self, 'ant.xml', 5)
        utils.EzPickle.__init__(self)

def __init__(self,
                 xml_file='hopper.xml',
                 forward_reward_weight=1.0,
                 ctrl_cost_weight=1e-3,
                 healthy_reward=1.0,
                 terminate_when_unhealthy=True,
                 healthy_state_range=(-100.0, 100.0),
                 healthy_z_range=(0.7, float('inf')),
                 healthy_angle_range=(-0.2, 0.2),
                 reset_noise_scale=5e-3,
                 exclude_current_positions_from_observation=True,
                 rgb_rendering_tracking=True):
        utils.EzPickle.__init__(**locals())

        self._forward_reward_weight = forward_reward_weight

        self._ctrl_cost_weight = ctrl_cost_weight

        self._healthy_reward = healthy_reward
        self._terminate_when_unhealthy = terminate_when_unhealthy

        self._healthy_state_range = healthy_state_range
        self._healthy_z_range = healthy_z_range
        self._healthy_angle_range = healthy_angle_range

        self._reset_noise_scale = reset_noise_scale

        self._exclude_current_positions_from_observation = (
            exclude_current_positions_from_observation)