How to use the stable-baselines.stable_baselines.common.identity_env.IdentityEnv function in stable-baselines

space = Box(low=low, high=high, shape=(1,), dtype=np.float32)
        super().__init__(ep_length=ep_length, space=space)
        self.eps = eps

    def step(self, action):
        reward = self._get_reward(action)
        self._choose_next_state()
        self.current_step += 1
        done = self.current_step >= self.ep_length
        return self.state, reward, done, {}

    def _get_reward(self, action):
        return 1 if (self.state - self.eps) <= action <= (self.state + self.eps) else 0


class IdentityEnvMultiDiscrete(IdentityEnv):
    def __init__(self, dim=1, ep_length=100):
        """
        Identity environment for testing purposes

        :param dim: (int) the size of the dimensions you want to learn
        :param ep_length: (int) the length of each episode in timesteps
        """
        space = MultiDiscrete([dim, dim])
        super().__init__(ep_length=ep_length, space=space)


class IdentityEnvMultiBinary(IdentityEnv):
    def __init__(self, dim=1, ep_length=100):
        """
        Identity environment for testing purposes

return 1 if (self.state - self.eps) <= action <= (self.state + self.eps) else 0


class IdentityEnvMultiDiscrete(IdentityEnv):
    def __init__(self, dim=1, ep_length=100):
        """
        Identity environment for testing purposes

        :param dim: (int) the size of the dimensions you want to learn
        :param ep_length: (int) the length of each episode in timesteps
        """
        space = MultiDiscrete([dim, dim])
        super().__init__(ep_length=ep_length, space=space)


class IdentityEnvMultiBinary(IdentityEnv):
    def __init__(self, dim=1, ep_length=100):
        """
        Identity environment for testing purposes

        :param dim: (int) the size of the dimensions you want to learn
        :param ep_length: (int) the length of each episode in timesteps
        """
        space = MultiBinary(dim)
        super().__init__(ep_length=ep_length, space=space)

self._choose_next_state()
        self.current_step += 1
        done = self.current_step >= self.ep_length
        return self.state, reward, done, {}

    def _choose_next_state(self):
        self.state = self.action_space.sample()

    def _get_reward(self, action):
        return 1 if np.all(self.state == action) else 0

    def render(self, mode='human'):
        pass


class IdentityEnvBox(IdentityEnv):
    def __init__(self, low=-1, high=1, eps=0.05, ep_length=100):
        """
        Identity environment for testing purposes

        :param low: (float) the lower bound of the box dim
        :param high: (float) the upper bound of the box dim
        :param eps: (float) the epsilon bound for correct value
        :param ep_length: (int) the length of each episode in timesteps
        """
        space = Box(low=low, high=high, shape=(1,), dtype=np.float32)
        super().__init__(ep_length=ep_length, space=space)
        self.eps = eps

    def step(self, action):
        reward = self._get_reward(action)
        self._choose_next_state()