Learning from Demonstrations and Human Evaluative Feedbacks: Handling Sparsity and Imperfection Using Inverse Reinforcement Learning Approach

Algorithm 1

framework.

(1)	Input: , feature , , and number of interaction steps
(2)
(3)
(4)	; ;
(5)	while teacher is not satisfied
(6)
(7)	Interact with the environment for steps
(8)
(9)	execute action according to
(10)	if teacher critique for is received
(11)
(12)
(13)
(14)	end interaction
(15)
(16)
(17)	end while
(18)	Output: