A Novel Behavioral Strategy for RoboCode Platform Based on Deep Q-Learning

Table 2

T-test results between the AI robot and Tracker and SpinBot robots.

Tracker vs. AI robot		SpinBot vs. AI robot
t Stat	−3.91654	t Stat	−7.43674
P (T ≤ t) one tail	0.002887	P(T ≤ t) one tail	0.000346
t Critical one-tail	1.894579	t Critical one-tail	2.015048
P (T ≤ t) two tail	0.005775	P(T ≤ t) two tail	0.000693
t Critical one-tail	2.364624	t Critical one-tail	2.570582