Offline Generalized Actor-Critic With Distance RegularizationOA
Offline Generalized Actor-Critic With Distance Regularization
Huanting Feng;Yuhu Cheng;Xuesong Wang
Engineering Research Center of Intelligent Control for Underground Space,Ministry of Education,and the School of Information and Control Engineering,China University of Mining and Technology,Xuzhou 221116,China||School of Intelligent Engineering,Jiangsu Vocational College of Information Technology,Wuxi 214153,ChinaEngineering Research Center of Intelligent Control for Underground Space,Ministry of Education,and the School of Information and Control Engineering,China University of Mining and Technology,Xuzhou 221116,ChinaEngineering Research Center of Intelligent Control for Underground Space,Ministry of Education,and the School of Information and Control Engineering,China University of Mining and Technology,Xuzhou 221116,China
Actor-criticdistance regularizationgeneralized Q-learningoffline reinforcement learningout-of-distribution(OOD).
Actor-criticdistance regularizationgeneralized Q-learningoffline reinforcement learningout-of-distribution(OOD).
《自动化学报（英文版）》 2026 (1)
57-71,15
This work was supported by the National Natural Science Foundation of China(62373364,62176259)and the Key Research and Development Program of Jiangsu Province(BE2022095).
评论