ICML-Doubly Robust Off-Policy Actor-Critic Convergence and Optimality

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

Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality

              Tengyu Xu 1 Zhuoran Yang 2 Zhaoran Wang 3 Yingbin Liang 1

             Abstract                 (Haarnoja et al., 2018), etc. However, these successes usu-
   Designing off-policy reinforcement learning al-        ally rely on the access to on-policy samples, i.e., samples
   gorithms is typically a very challenging task, be-      collected online from on-policy visitation (or stationary)
   cause a desirable itera ...

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏0 回帖

关键词：Convergence Optimality converge optimal Policy