Ranked-trajectory based recursive inverse reinforcement learning for extrapolation of reward function
Ranked-trajectory based recursive inverse reinforcement learning for extrapolation of reward function
复制标题
用于外推奖励函数的基于排序轨迹的递归逆强化学习
DOI:
--
复制
发表时间:
2021
期刊:
影响因子:
--
通讯作者:
Gakuto Masuyama
中科院分区:
文献类型:
--
作者:
Takashi Aota;Gakuto Masuyama