LRP-based Policy Pruning and Distillation of Reinforcement Learning Agents for Embedded Systems

Rui Xu, Siyu Luan, Zonghua Gu 0001, Qingling Zhao, Gang Chen 0023. LRP-based Policy Pruning and Distillation of Reinforcement Learning Agents for Embedded Systems. In 25th IEEE International Symposium On Real-Time Distributed Computing, ISORC 2022, Västerås, Sweden, May 17-18, 2022. pages 1-8, IEEE, 2022. [doi]

Abstract

Abstract is missing.