ICML-Monotonic Robust Policy Optimization with Model Discrepancy

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

Monotonic Robust Policy Optimization with Model Discrepancy

           Yuankun Jiang 1 Chenglin Li 2 Wenrui Dai 1 Junni Zou 1 Hongkai Xiong 2

             Abstract               control tasks, e.g., playing computer games with human-
    State-of-the-art deep reinforcement learning       level performance (Mnih et al., 2013; Silver et al., 2018)
    (DRL) algorithms tend to overt due to the model     and trafc signal control (Chen et al., 2020). DRL often
    discrepancy between source and t ...

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：Optimization monotonic robust Policy ATION