[其他] ICML-Average-Reward Off-Policy Policy Evaluation with Function Approximation [推广有奖]

1关注
167
粉丝

已卖：5667份资源

泰斗

还不是VIP/贵宾

威望: 0 级
论坛币: 13312 个
通用积分: 711.3950
学术水平: 459 点
热心指数: 484 点
信用等级: 414 点
经验: 116069 点
帖子: 4684
精华: 0
在线时间: 16723 小时
注册时间: 2013-1-2
最后登录: 2025-12-14

楼主

Mujahida

发表于 2025-8-10 21:22:43 |AI写论文

是否 +2 论坛币

k人参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

Average-Reward Off-Policy Policy Evaluation with Function Approximation

         Shangtong Zhang 1 * Yi Wan 2 * Richard S. Sutton 2 Shimon Whiteson 1

         Abstract                which aim to generate a policy that maximizes the reward
                              rate by iteratively improving the policy using its estimated
We consider off-policy policy evaluation with       differential value function (see, e.g., Howard (1960); Konda
function approximation (FA) in av ...