Balance Between Efficient and Effective Learning: Dense2Sparse Reward Shaping for Robot Manipulation with Environment Uncertainty

Kun Dong, Yongle Luo, Erkang Cheng, Zhiyong Sun, Lili Zhao, Qiang Zhang, Chao Zhou, Bo Song. Balance Between Efficient and Effective Learning: Dense2Sparse Reward Shaping for Robot Manipulation with Environment Uncertainty. In IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2022, Sapporo, Japan, July 11-15, 2022. pages 1192-1198, IEEE, 2022. [doi]

Abstract

Abstract is missing.