A novel multi-step reinforcement learning method for solving reward hacking
Yuan, Yinlong, Yu, Zhu Liang, Gu, Zhenghui, Deng, Xiaoyan, Li, YuanqingLanguage:
english
Journal:
Applied Intelligence
DOI:
10.1007/s10489-019-01417-4
Date:
February, 2019
File:
PDF, 4.69 MB
english, 2019