1. Achieving efficient interpretability of reinforcement learning via policy distillation and selective input gradient regularization. (April 2023) Authors: Xing, Jinwei; Nagata, Takashi; Zou, Xinyun; Neftci, Emre; Krichmar, Jeffrey L. Journal: Neural networks Issue: Volume 161(2023) Page Start: 228 Record Type: Journal Article View Content: Available online (eLD content is only available in our Reading Rooms) ↗