[其他] ICML-High Confidence Generalization for Reinforcement Learning [推广有奖]

1关注
167
粉丝

已卖：5678份资源

泰斗

还不是VIP/贵宾

威望: 0 级
论坛币: 13312 个
通用积分: 718.1716
学术水平: 459 点
热心指数: 484 点
信用等级: 414 点
经验: 116269 点
帖子: 4686
精华: 0
在线时间: 16731 小时
注册时间: 2013-1-2
最后登录: 2026-1-21

楼主

Mujahida

发表于 2025-8-10 13:52:06 |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

High Confidence Generalization for Reinforcement Learning

James E. Kostas 1 Yash Chandak 1 Scott M. Jordan 1 Georgios Theocharous 2 Philip S. Thomas 1

         Abstract                formance on MDPs drawn from the distribution, including
                              MDPs not in the training set.
We present several classes of reinforcement learn-
ing algorithms that safely generalize to Markov       HCGAs first train using a standard RL algorithm and then
decision proc ...