dqn_utils.py 文件源码

def build_graph(self):
        self.ph_local_step = tf.placeholder(tf.int64, [])
        self.ph_q_value = tf.placeholder(tf.float32, [None, dqn_config.config.output.action_size])

        if dqn_config.config.eps.stochastic:
            decay_steps = int(np.random.uniform(*dqn_config.config.eps.decay_steps))
        else:
            decay_steps = dqn_config.config.eps.decay_steps

        eps = tf.train.polynomial_decay(dqn_config.config.eps.initial,
                                        self.ph_local_step,
                                        decay_steps,
                                        dqn_config.config.eps.end)

        return tf.cond(tf.less(tf.random_uniform([]), eps),
                       lambda: tf.random_uniform([], 0, dqn_config.config.output.action_size, dtype=tf.int32),
                       lambda: tf.cast(tf.squeeze(tf.argmax(self.ph_q_value, axis=1)), tf.int32))