LinUCBAgentClass.py 文件源码

def _compute_score(self, context):
        '''
        Args:
            context (list)

        Returns:
            (dict):
                K (str): action
                V (float): score
        '''

        a_inv = self.model['act_inv']
        theta = self.model['theta']

        estimated_reward = {}
        uncertainty = {}
        score_dict = {}
        max_score = 0
        for action_id in xrange(len(self.actions)):
            action_context = np.reshape(context[action_id], (-1, 1))
            estimated_reward[action_id] = float(theta[action_id].T.dot(action_context))
            uncertainty[action_id] = float(self.alpha * np.sqrt(action_context.T.dot(a_inv[action_id]).dot(action_context)))
            score_dict[action_id] = estimated_reward[action_id] + uncertainty[action_id]

        return score_dict