Reinforcement Learning-Based Backstepping Control for Container Cranes

Table 1

Parameters of the crane and the controller.

	Parameter	Value
Container crane	m1 (kg)	4.5
	m2 (kg)	1
	l (m)	0.7
Controller	β1	1
	[ψmax, ψmin]	[0, 4e^−2]
	[Г1,min, Г1,max]	[−1.5e^−3, 1.5e^−3]
	[Г2,min, Г2,max]	[−2e^−2, 2e^−2]
	η	0.1
	λ	0.5