Conference paper
Hybrid reinforcement learning with expert state sequences
Xiaoxiao Guo, Shiyu Chang, et al.
AAAI 2019
XPROBE extends the teaching-by-showing method of robot programming to the teaching of sensor strategies. The XPROBE system has a dialogue with the user, during which the user is directed to guide the robot through an example of the desired task. XPROBE then automatically writes an AML program that includes sensory decision making as a generalization of the taught example. © 1984, Sage Publications. All rights reserved.
Xiaoxiao Guo, Shiyu Chang, et al.
AAAI 2019
Shai Fine, Yishay Mansour
Machine Learning
Ryan Johnson, Ippokratis Pandis
CIDR 2013
Guo-Jun Qi, Charu Aggarwal, et al.
IEEE TPAMI