An Intelligent Optimization Strategy Based on Deep Reinforcement Learning for Step Counting

Algorithm 1 The proposed approach.

	Random initialize the parameter of strategy network, Set learning rate parameter, total rounds
(1)	for do
(2)	Get initialization status
(3)	for . do
(4)	Get according to
(5)	Accumulate the reward according to
(6)	end for
(7)	Get the step sum unit
(8)	Get reward according to
(9)	for . do
(10)	.
(11)	According to formula (4), optimizing parameters
(12)	Updating parameters:
(13)	end for
(14)	end for