Achieving efficient interpretability of reinforcement learning via policy distillation and selective input gradient regularization - researchr publication

researchr

You are not signed in
Sign in
Sign up

Jinwei Xing, Takashi Nagata, Xinyun Zou, Emre Neftci, Jeffrey L. Krichmar. Achieving efficient interpretability of reinforcement learning via policy distillation and selective input gradient regularization. Neural Networks, 161:228-241, April 2023. [doi]

Abstract is missing.

runs on WebDSL