Generalizable Episodic Memory for Deep Reinforcement Learning
Hao Hu 1 Jianing Ye 2 Guangxiang Zhu 1 Zhizhou Ren 3 Chongjie Zhang 1
Abstract
Discrete Episodic Memory
Episodic memory-based methods can rapidly
latch onto past successful strategies by a non- Key Value
parametric memory and improve sample effi-
ciency of traditional reinforcement learning. How-
ever, little effort is put into the continuou ...


雷达卡




京公网安备 11010802022788号







