[其他] ICML-Provably Correct Optimization and Exploration with Non-linear Policies [推广有奖]

1关注
167
粉丝

已卖：5665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: 115999 点
帖子: 4683
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 2025-7-27 18:32:10 |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

Provably Correct Optimization and Exploration with Non-linear Policies

               Fei Feng 1 Wotao Yin 1 Alekh Agarwal 2 Lin Yang 3

         Abstract             rer & Geist, 2014; Geist et al., 2019; Abbasi-Yadkori et al.,
Policy optimization methods remain a powerful    2019; Agarwal et al., 2020c; Bhandari & Russo, 2019) when
workhorse in empirical Reinforcement Learning    the agent has access to a distribution over states which is
(RL), with a focus on neur ...