Learn to Make Decision with Small Data for Autonomous Driving: Deep Gaussian Process and Feedback Control

Table 4

Comparison of three methods.

Methods	Times	Total rewards	Training time (h)	Training data	Pass CG
DDPG	338	28148.09	16		Yes
Deep GP	170	9917.06	1.5	338	No
Deep GP + Feedback	380	26555.32	1.5	338	Yes