The EMPATHIC Framework for Task Learning from Implicit Human Feedback.
作者： Scott Niekum , Alessandro Allievi , Peter Stone , W. Bradley Knox , Yuchen Cui
DOI:
关键词: Leverage (statistics) 、 Robot 、 Computer science 、 Artificial neural network 、 Teaching method 、 Task learning 、 Facial expression 、 Human–computer interaction 、 Gesture
摘要: … proxies for a reaction mapping by watching the reactions of the … their inferred reward, which we refer to as the rewardranking … This work focuses on predicting task statistics from human …
arxiv.org
harvard.edu参考文章(2)
Diederik P. Kingma, Jimmy Ba, Adam: A Method for Stochastic Optimization arXiv: Learning. ,(2014)
Brenna D. Argall, Sonia Chernova, Manuela Veloso, Brett Browning, A survey of robot learning from demonstration Robotics and Autonomous Systems. ,vol. 57, pp. 469- 483 ,(2009) , 10.1016/J.ROBOT.2008.10.024