Path-Integral-Based Reinforcement Learning Algorithm for Goal-Directed Locomotion of Snake-Shaped Robot

Algorithm 1

The algorithm steps of goal-directed locomotion.

	Initialize:
	repeat
	(for each episode) Initialize:
	While is not
	If (Probability less than)
	choose
	Else
	Random choose
	End
	If (There is no collision)
	Take action, returnand
	Update
	repeat
	until
	until The task of goal-directed locomotion is finished
	End