Supervised-actor-critic reinforcement learning for intelligent mechanical ventilation and sedative dosing in intensive care units

Table 3 The AR and MSE of learned polices using SAC and AC algorithms on expert data, single intubation and multiple intubation

Strategy	Expert data		Single intubation		Multiple intubation
	MSE	AR	MSE	AR	MSE	AR
SAC	2.52	37%	2.71	38%	2.28	47%
AC	3.01	34%	3.15	35%	3.08	41%

ISSN: 1472-6947