self_driving_V1.1.py 文件源码

def get_reward(self, next_state):
        p, v, ID, a = next_state['p'], next_state['v'], int(next_state['ID']), next_state['a']
        p_f, v_f, l_f = next_state['p_l1'], next_state['v_l1'], next_state['l_l1']

        distance = (p_f-l_f) - p
        h = distance / v
        h = 10 if np.isinf(h) else h        # avoid reward to inf
        #desired_headway = 1

        if h < 1.3 and h >= 1:
            reward = 4*(1.3-h)
        elif h > 0.7 and h < 1:
            reward = 4*(h-0.7)
        elif h >= 1.3:
            reward = -2*(h-1.3)
        else:
            # h<=0.7
            reward = -1*(0.7-h)

        self.cars[ID].reward = reward
        return reward