nec_agent.py 文件源码

def test(self, nb_episodes=1, maximum_episode_length=5000000):
    def evaluate_episode():
      reward = 0
      observation = self.env.reset()
      for _ in range(maximum_episode_length):
        action = self.choose_action(self.embedding_network(Variable(Tensor(observation)).unsqueeze(0)), 0)
        observation, immediate_reward, finished, info = self.env.step(action)
        reward += immediate_reward
        if finished:
          break
      return reward

    r = 0
    for _ in range(nb_episodes):
      r += evaluate_episode()
    return r / nb_episodes