TY - JOUR
AU - Xing, Jinwei
AU - Nagata, Takashi
AU - Zou, Xinyun
AU - Neftci, Emre
AU - Krichmar, Jeffrey L.
TI - Achieving efficient interpretability of reinforcement learning via policy distillation and selective input gradient regularization
JO - Neural networks
VL - 161
SN - 0893-6080
CY - Amsterdam
PB - Elsevier
M1 - FZJ-2024-01831
SP - 228 - 241
PY - 2023
LB - PUB:(DE-HGF)16
C6 - 36774862
UR - <Go to ISI:>//WOS:000943188100001
DO - DOI:10.1016/j.neunet.2023.01.025
UR - https://juser.fz-juelich.de/record/1023826
ER -