Here’s What I’ve Learned: Asking Questions that Reveal Reward Learning
Here’s What I’ve Learned: Asking Questions that Reveal Reward Learning
复制标题
这是我学到的:提出能够奖励学习的问题
DOI:
--
复制
发表时间:
2021
影响因子:
5.1
通讯作者:
Dylan P. Losey
中科院分区:
文献类型:
--
作者:
Soheil Habibian;Ananth Jonnavittula;Dylan P. Losey
Robots can learn from humans by asking questions. In these questions, the robot demonstrates a few different behaviors and asks the human for their favorite. But how should robots choose which questions to ask? Today’s robots optimize for informative questions that actively probe the human’s preferences as efficiently as possible. But while informative questions make sense from the robot’s perspective, human onlookers may find them arbitrary and misleading. For example, consider an assistive robot learning to put away the dishes. Based on your answers to previous questions this robot knows where it should stack each dish; however, the robot is unsure about right height to carry these dishes. A robot optimizing only for informative questions focuses purely on this height: it shows trajectories that carry the plates near or far from the table, regardless of whether or not they stack the dishes correctly. As a result, when we see this question, we mistakenly think that the robot is still confused about where to stack the dishes! In this article, we formalize active preference-based learning from the human’s perspective. We hypothesize that—from the human’s point-of-view —the robot’s questions reveal what the robot has and has not learned. Our insight enables robots to use questions to make their learning process transparent to the human operator. We develop and test a model that robots can leverage to relate the questions they ask to the information these questions reveal. We then introduce a tradeoff between informative and revealing questions that considers both human and robot perspectives: a robot that optimizes for this tradeoff actively gathers information from the human while simultaneously keeping the human up to date with what it has learned. We evaluate our approach across simulations, online surveys, and in-person user studies. We find that robots, which consider the human’s point of view learn just as quickly as state-of-the-art baselines while also communicating what they have learned to the human operator. Videos of our user studies and results are available here: https://youtu.be/tC6y_jHN7Vw.
登录
查看更多内容
DOI:
--
发表时间:
2019-04
期刊:
--
影响因子:
--
作者:
Daniel S. Brown;Wonjoon Goo;P. Nagarajan;S. Niekum
通讯作者:
Daniel S. Brown;Wonjoon Goo;P. Nagarajan;S. Niekum
DOI:
10.1177/02783649211041652
发表时间:
2021
期刊:
The International Journal of Robotics Research
影响因子:
--
作者:
Bıyık, Erdem;Losey, Dylan P.;Palan, Malayandi;Landolfi, Nicholas C.;Shevchuk, Gleb;Sadigh, Dorsa
通讯作者:
Sadigh, Dorsa
DOI:
--
发表时间:
2019
期刊:
Proceedings of the 3rd Conference on Robot Learning
影响因子:
--
作者:
Erdem Biyik, Malayandi Palan
通讯作者:
Erdem Biyik, Malayandi Palan
DOI:
--
发表时间:
2017-10
期刊:
--
影响因子:
--
作者:
Jesse Thomason;Aishwarya Padmakumar;Jivko Sinapov;Justin W. Hart;P. Stone;R. Mooney
通讯作者:
Jesse Thomason;Aishwarya Padmakumar;Jivko Sinapov;Justin W. Hart;P. Stone;R. Mooney
影响因子:
3.5
作者:
Huang, Sandy H.;Held, David;Dragan, Anca D.
通讯作者:
Dragan, Anca D.