Research on Dynamic Path Planning of Wheeled Robot Based on Deep Reinforcement Learning on the Slope Ground

Table 2

Comparison of TDDQN and D^∗ experimental results. (Time (s)).

Algorithm	Target point
	Start point	A		B	C
D^∗	X		55.2	51.6	52.1
	Y		32.8	49.7	48.8
TDDQN	X		45.3	39.8	41.4
	Y		27.4	38.6	39.2