[其他] ICML-Robust Policy Gradient against Strong Data Corruption [推广有奖]

1关注
167
粉丝

已卖：5690份资源

泰斗

还不是VIP/贵宾

威望: 0 级
论坛币: 13312 个
通用积分: 769.6789
学术水平: 459 点
热心指数: 484 点
信用等级: 414 点
经验: 116379 点
帖子: 4688
精华: 0
在线时间: 16731 小时
注册时间: 2013-1-2
最后登录: 2026-2-9

楼主

Mujahida

发表于 2025-7-27 14:24:07 |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

Robust Policy Gradient against Strong Data Corruption

            Xuezhou Zhang 1 Yiding Chen 1 Jerry Zhu 1 Wen Sun 2

         Abstract                highly noisy data, such as autonomous driving, quantitative
                              trading, or medical diagnosis.
We study the problem of robust reinforcement
learning under adversarial corruption on both re-    In fact, data corruption can be a larger threat in the RL
wards and transitions. Our attack model assumes  ...