ddpg_cartpole.py 文件源码

def action_given(self, state, add_noise=False):
    # feed explicitly provided state
    actions = tf.get_default_session().run(self.output_action,
                                           feed_dict={self.input_state: [state],
                                                      base_network.IS_TRAINING: False})

    # NOTE: noise is added _outside_ tf graph. we do this simply because the noisy output
    # is never used for any part of computation graph required for online training. it's
    # only used during training after being the replay buffer.
    if add_noise:
      if VERBOSE_DEBUG:
        pre_noise = str(actions)
      actions[0] += self.exploration_noise.sample()
      actions = np.clip(1, -1, actions)  # action output is _always_ (-1, 1)
      if VERBOSE_DEBUG:
        print "TRAIN action_given pre_noise %s post_noise %s" % (pre_noise, actions)

    return actions