lrpg_cartpole.py 文件源码

def train(self, observations, actions, advantages):
    """ take one training step given observations, actions and subsequent advantages"""
    if VERBOSE_DEBUG:
      print "TRAIN"
      print "observations", np.stack(observations)
      print "actions", actions
      print "advantages", advantages
      _, loss = tf.get_default_session().run([self.train_op, self.loss],
                                             feed_dict={self.observations: observations,
                                                        self.actions: actions,
                                                        self.advantages: advantages})

    else:
      _, loss = tf.get_default_session().run([self.train_op, self.loss],
                                             feed_dict={self.observations: observations,
                                                        self.actions: actions,
                                                        self.advantages: advantages})
    return float(loss)