[其他] ICML-Provably Efficient Fictitious Play Policy Optimization for Zero-Sum Ma ... [推广有奖]

1关注
167
粉丝

已卖：5641份资源

泰斗

还不是VIP/贵宾

威望: 0 级
论坛币: 13322 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: 115899 点
帖子: 4676
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 18:45:42 |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 Efficient Fictitious Play Policy Optimization for
      Zero-Sum Markov Games with Structured Transitions

         Shuang Qiu 1 Xiaohan Wei 2 Jieping Ye 1 Zhaoran Wang 3 Zhuoran Yang 4

         Abstract                understanding of multi-agent policy optimization, especially
                              the zero-sum Markov game (Littman, 1994) via policy opti-
While single-agent policy optimization in a fixed    mization, lags rather behind. Most recent works  ...