def __init__(self, sess, ob_space, ac_space, nbatch, nsteps, reuse=False, **conv_kwargs): #pylint: disable=W0613
        self.pdtype = make_pdtype(ac_space)
        #X, processed_x = observation_input(ob_space, nbatch)
        X, processed_x = observation_input(ob_space, None)
        with tf.variable_scope("model", reuse=reuse):
            h = nature_cnn(processed_x, **conv_kwargs)
            vf = fc(h, 'v', 1)[:,0]
            self.pd, self.pi = self.pdtype.pdfromlatent(h, init_scale=0.01)

        a0 = self.pd.sample()
        neglogp0 = self.pd.neglogp(a0)
        self.initial_state = None
        
        self.entropy = cat_entropy(self.pi)

        def step(ob, *_args, **_kwargs):
            a, v, neglogp = sess.run([a0, vf, neglogp0], {X:ob})
            return a, v, self.initial_state, neglogp

        def value(ob, *_args, **_kwargs):
            return sess.run(vf, {X:ob})

        def neg_log_prob(actions):
            return tf.nn.sparse_softmax_cross_entropy_with_logits(
                logits=self.pi, labels=actions)

        self.X = X
        self.vf = vf
        self.step = step
        self.value = value
        self.neg_log_prob = neg_log_prob