Teaching a Robot Tasks of Arbitrary Complexity via Human Feedback
Teaching a Robot Tasks of Arbitrary Complexity via Human Feedback
复制标题
通过人类反馈教机器人执行任意复杂的任务
DOI:
10.1145/3319502.3374824
复制
发表时间:
2020
期刊:
影响因子:
--
通讯作者:
Littman, Michael L.
中科院分区:
文献类型:
--
作者:
Wang, Guan;Trimbach, Carl;Lee, Jun Ki;Ho, Mark K.;Littman, Michael L.
This paper addresses the problem of training a robot to carry out temporal tasks of arbitrary complexity via evaluative human feedback that can be inaccurate. A key idea explored in our work is a kind of curriculum learning---training the robot to master simple tasks and then building up to more complex tasks. We show how a training procedure, using knowledge of the formal task representation, can decompose and train any task efficiently in the size of its representation. We further provide a set of experiments that support the claim that non-expert human trainers can decompose tasks in a way that is consistent with our theoretical results, with more than half of participants successfully training all of our experimental missions. We compared our algorithm with existing approaches and our experimental results suggest that our method outperforms alternatives, especially when feedback contains mistakes.
登录
查看更多内容
DOI:
--
发表时间:
2017
期刊:
arXiv.org
影响因子:
--
作者:
Littman, Michael L.;Topcu, Ufuk;Fu, Jie;Isbell, Charles;Wen, Min;MacGlashan, James
通讯作者:
MacGlashan, James
影响因子:
3.4
作者:
Ho, Mark K.;MacGlashan, James;Cushman, Fiery
通讯作者:
Cushman, Fiery
DOI:
--
发表时间:
1996
期刊:
AAAI/IAAI, Vol. 2
影响因子:
--
作者:
F. Bacchus;Craig Boutilier;Adam J. Grove
通讯作者:
Adam J. Grove
DOI:
--
发表时间:
2016
期刊:
Theory and Practice of Formal Methods
影响因子:
--
作者:
D. Ancona;Angelo Ferrando;V. Mascardi
通讯作者:
V. Mascardi
DOI:
10.1109/tetci.2018.2829980
发表时间:
2017-05
影响因子:
5.3
作者:
Bei Peng;J. MacGlashan;R. Loftin;M. Littman;David L. Roberts;Matthew E. Taylor
通讯作者:
Bei Peng;J. MacGlashan;R. Loftin;M. Littman;David L. Roberts;Matthew E. Taylor