eye_experiment.py 文件源码

def act(self, observation, reward):
        """
        Interact with and learn from the environment.
        Returns the suggested control vector.
        """
        observation = np.ravel_multi_index(observation, self.input_shape)
        self.xp_q.update_reward(reward)
        action = self.best_action(observation)
        self.xp_q.add(observation, action)
        action = np.unravel_index(action, self.output_shape)
        return action