Online Pedagogical Tutorial Tactics Optimization Using Genetic-Based Reinforcement Learning

Table 2

The median (Q1–Q3) of the normalized test scores of the two groups in experiment .

Test	Student group		value
	NormGain	RevNormGain
Pretest	0.9	0.875	0.55
	(0.775–0.95)	(0.7875–0.9125)
Posttest	0.95	0.875	( < .001)
	(0.95–1)	(0.7875–0.9125)
value	.008	1