%0 Journal Article
%A Xing, Jinwei
%A Nagata, Takashi
%A Zou, Xinyun
%A Neftci, Emre
%A Krichmar, Jeffrey L.
%T Achieving efficient interpretability of reinforcement learning via policy distillation and selective input gradient regularization
%J Neural networks
%V 161
%@ 0893-6080
%C Amsterdam
%I Elsevier
%M FZJ-2024-01831
%P 228 - 241
%D 2023
%F PUB:(DE-HGF)16
%9 Journal Article
%$ 36774862
%U <Go to ISI:>//WOS:000943188100001
%R 10.1016/j.neunet.2023.01.025
%U https://juser.fz-juelich.de/record/1023826