Achieving efficient interpretability of reinforcement learning via policy distillation and selective input gradient regularization
| Autor: | Xing, Jinwei, Nagata, Takashi, Zou, Xinyun, Neftci, Emre, Krichmar, Jeffrey L. |
|---|---|
| Zdroj: | In Neural Networks April 2023 161:228-241 |
| Databáze: | ScienceDirect |
| Externí odkaz: |
|
Full Text from ScienceDirect