How to use the stable-baselines.stable_baselines.acktr.acktr.ACKTR function in stable-baselines

self.vf_fisher = None
        self.joint_fisher = None
        self.grads_check = None
        self.optim = None
        self.train_op = None
        self.q_runner = None
        self.learning_rate_schedule = None
        self.proba_step = None
        self.value = None
        self.initial_state = None
        self.n_batch = None
        self.summary = None
        self.trained = False
        self.continuous_actions = False

        super(ACKTR, self).__init__(policy=policy, env=env, verbose=verbose, requires_vec_env=True,
                                    _init_setup_model=_init_setup_model, policy_kwargs=policy_kwargs,
                                    seed=seed, n_cpu_tf_sess=n_cpu_tf_sess)

        if _init_setup_model:
            self.setup_model()