A Knowledge-Fusion Ranking System with an Attention Network for Making Assignment Recommendations

Algorithm 1

KFRank learning.

Input: assignment records , learning rate , discount factor , and reward function
Output:
(1)	Initialize with random values
(2)	updated state in an episode (, ), Algorithm 2
(3)
(4)	fordo
(5)	sample ranking in an episode
(6)	fortodo
(7)	Sample an action
(8)
(9)	Append at the end of
(10)	State transition
(11)	end for
(12)	fortodo
(13)
(14)
(15)	end for
(16)
(17)	end for