mainPlay.py 文件源码

def main():

    dqn = DQN(ENV_NAME, DOUBLE_DQN, DUELING_DQN, PER, TRAINING, RENDER)

    init_op = tf.group(tf.global_variables_initializer(), tf.local_variables_initializer())

    with tf.Session() as sess:

        sess.run(init_op)
        #tries to restore a trained model and play!
        dqn.util.restore_graph(sess,forTrain = TRAINING)

        for ep in tqdm(range(MAX_EPISODES)):# for episodes

            print("Episode no. {} :".format(ep))

            dqn.playing(sess)

            print('Episode %d: totalEpReward = %.2f , took: %.3f mins' % (ep, dqn.totalReward,dqn.duration/60.0))


#RUN...