agent.py 文件源码

def __init__(self, config, environment, optimizer, lr_op):
    super(Agent, self).__init__(config)
    self.weight_dir = 'weights'

    self.env = environment
    self.history = History(self.config)

    self.lr_op = lr_op
    self.optimizer = optimizer

    self.step_op = tf.Variable(0, trainable=False, name='step')
    self.step_inc_op = self.step_op.assign_add(1, use_locking=True)
    self.build_dqn()

    self.saver = tf.train.Saver(self.w.values() + [self.step_op], max_to_keep=30)
    self.summary_op = tf.merge_all_summaries()
    self.init_op = tf.initialize_all_variables()