您可以使用以下代码来计算奖励值:

def calculate_reward(numer):
    TOTAL_NUM_STEPS_1st = 15*22
    TOTAL_NUM_STEPS_2nd = 15*23
    TOTAL_NUM_STEPS_3rd = 15*24
    
    reward = 0
    if numer == TOTAL_NUM_STEPS_3rd:
        reward = 10
    elif numer == TOTAL_NUM_STEPS_2nd:
        reward = 5
    elif numer == TOTAL_NUM_STEPS_1st:
        reward = 3
    
    return reward

numer = 15 * 22  # 设置numer的值
reward = calculate_reward(numer)
print(reward)

根据您提供的要求,当numer的值等于TOTAL_NUM_STEPS_3rd时,奖励为10;当numer的值等于TOTAL_NUM_STEPS_2nd时,奖励为5;当numer的值等于TOTAL_NUM_STEPS_1st时,奖励为3。您可以根据需要修改numer的值来计算相应的奖励

python 算式 TOTAL_NUM_STEPS_1st = 1522 TOTAL_NUM_STEPS_2nd = 1523 TOTAL_NUM_STEPS_3rd = 1524当numer 越接近符合TOTAL_NUM_STEPS_3rd 或者TOTAL_NUM_STEPS_2nd 或者 TOTAL_NUM_STEPS_1st 的时候 奖励越好

原文地址: https://www.cveoy.top/t/topic/inOK 著作权归作者所有。请勿转载和采集!

免费AI点我,无需注册和登录