[其他] ICML-Towards Tight Bounds on the Sample Complexity of Average-reward MDPs [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: 116099 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: 2026-1-8

楼主

Mujahida

发表于 2025-7-27 09:59:22 |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

Towards Tight Bounds on the Sample Complexity
               of Average-reward MDPs

                        Yujia Jin 1 Aaron Sidford 1

            Abstract             making under uncertainty and reinforcement learning (Puter-
                              man, 2014; Sutton & Barto, 2018). It is a prominent theoret-
We prove new upper and lower bounds for sample    ical test-bed for learning algorithms and has been studied ex-
complexity of finding an -optimal poli ...